Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to social injustice and inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Negative treatment or discrimination

    np_acts-logits-general · gemini-2.0-flash

    experiencing exclusion or discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.70
     nakalista
    -0.69
     мәкалә
    -0.66
    onViewCreated
    -0.65
     distraction
    -0.62
    DebuggerNonUser
    -0.61
    aarrggbb
    -0.61
     noDo
    -0.61
    millimeters
    -0.60
    DebuggerStep
    -0.59
    POSITIVE LOGITS
     marginalized
    0.86
     discriminated
    0.80
     mist
    0.74
     ostra
    0.73
     margin
    0.72
     neglected
    0.71
     ignored
    0.69
     excluded
    0.67
     stigmati
    0.66
     overlooked
    0.65
    Act Density 0.298%

    No Known Activations