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

    Neuronpedia

    INDEX
    Explanations

    phrases that signal connections between concepts or ideas

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

    following "and"

    np_acts-logits-general · gemini-2.0-flash

    social justice and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    engertian
    -0.50
     virš
    -0.50
     urmă
    -0.48
     complète
    -0.48
    ariest
    -0.47
    DockStyle
    -0.47
     isolado
    -0.45
     situazione
    -0.44
     oprot
    -0.44
     attore
    -0.44
    POSITIVE LOGITS
    UnusedPrivate
    0.83
    Хьажоргаш
    0.81
     social
    0.80
     nakalista
    0.78
    writeFieldEnd
    0.71
    ViewInit
    0.68
    specifically
    0.67
    DrawerToggle
    0.66
    social
    0.65
    NameInMap
    0.65
    Act Density 0.322%

    No Known Activations