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

    Neuronpedia

    INDEX
    Explanations

    giving or receiving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.29
     purpoſe
    -1.15
    ^(@)
    -1.09
     Majefty
    -1.05
     HasFactory
    -1.03
     raiſ
    -1.00
     houſe
    -0.98
     myſelf
    -0.97
     Jefus
    -0.96
     Houſe
    -0.94
    POSITIVE LOGITS
     for
    0.88
    .
    0.66
     to
    0.65
    !
    0.62
    ,
    0.62
     -
    0.60
    ↵
    0.60
     
    0.58
     For
    0.55
    for
    0.53
    Act Density 0.070%

    No Known Activations