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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xmax
    -0.07
    -0.07
    enticated
    -0.07
    (Form
    -0.07
     LH
    -0.07
     succinct
    -0.06
    以及
    -0.06
    ith
    -0.06
    üp
    -0.06
    (ms
    -0.06
    POSITIVE LOGITS
    �
    0.07
     tez
    0.06
    _STAT
    0.06
     něco
    0.06
    _assets
    0.06
    폴
    0.06
     Rosie
    0.06
    レビ
    0.06
     SPORT
    0.06
     والت
    0.06
    Act Density 0.053%

    No Known Activations