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

    Neuronpedia

    INDEX
    Explanations

    ys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ys
    -2.02
    YS
    -1.59
    ck
    -1.24
    ysa
    -1.16
     roll
    -1.05
    ysy
    -0.99
    ysk
    -0.95
    yste
    -0.94
    yser
    -0.92
    ysh
    -0.85
    POSITIVE LOGITS
     tartalomajánló
    1.03
     Efq
    1.00
     Monfieur
    0.92
     itſelf
    0.91
     myſelf
    0.91
     <>",
    0.88
    存于互联网档案馆
    0.82
     ſeveral
    0.81
     مشين
    0.79
     Jefus
    0.79
    Act Density 1.173%

    No Known Activations