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

    Neuronpedia

    INDEX
    Explanations

    topics related to affirmative action and university admissions policies

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

    students, action, percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hésite
    -0.42
    первых
    -0.37
    setObjectName
    -0.36
    rrggbb
    -0.36
     wife
    -0.35
     waveform
    -0.34
    AccessorTable
    -0.34
     scales
    -0.34
     vettoriale
    -0.34
    PhysRevD
    -0.32
    POSITIVE LOGITS
     saites
    0.65
    Talent
    0.64
    исленность
    0.63
     Talents
    0.62
     nonUne
    0.62
    Personendaten
    0.62
     HasFactory
    0.60
     Gifted
    0.60
     талан
    0.59
    elite
    0.56
    Act Density 0.081%

    No Known Activations