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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coll
    -0.07
    acting
    -0.07
     ent
    -0.07
    Miami
    -0.07
    unsch
    -0.07
    ым
    -0.06
    ignon
    -0.06
    _ent
    -0.06
     дат
    -0.06
     joining
    -0.06
    POSITIVE LOGITS
     bids
    0.06
    2
    0.06
     MOUSE
    0.06
    .setMax
    0.06
     bị
    0.06
     Criminal
    0.06
     kırmızı
    0.06
    声音
    0.05
    �
    0.05
    .cls
    0.05
    Act Density 0.017%

    No Known Activations