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

    Neuronpedia

    INDEX
    Explanations

    terms related to systems and regulations

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

    systems and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.44
    didSet
    -0.37
     specially
    -0.37
     differenza
    -0.36
     confirmado
    -0.34
     special
    -0.33
     duly
    -0.33
     keen
    -0.33
    WEBPACK
    -0.31
     différence
    -0.31
    POSITIVE LOGITS
     outdated
    0.69
     archaic
    0.67
     architecture
    0.66
     methodologies
    0.66
    Outdated
    0.66
     governance
    0.65
     handling
    0.65
     infrastructure
    0.65
    ſelves
    0.64
     antiquated
    0.64
    Act Density 0.044%

    No Known Activations