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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in the context of their professional roles or statements

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

    first names followed by last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ніципалі
    -0.63
     متعلقه
    -0.51
    tvguidetime
    -0.48
    WebControls
    -0.48
    󠁴
    -0.46
     betweenstory
    -0.45
     للمعارف
    -0.44
    migrationBuilder
    -0.44
    VideoCapture
    -0.43
    lorette
    -0.42
    POSITIVE LOGITS
    findpost
    0.48
     EnglishChoose
    0.44
     Administrativna
    0.44
    AxisAlignment
    0.43
    didReceive
    0.42
    cessite
    0.42
    InjectAttribute
    0.41
     secretary
    0.39
    WillAppear
    0.39
    Amicalement
    0.39
    Act Density 0.014%

    No Known Activations