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

    Neuronpedia

    INDEX
    Explanations

    Wal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۲۲
    -0.06
    /latest
    -0.06
    (weight
    -0.06
    Dirty
    -0.06
    spoken
    -0.06
    ---↵
    -0.05
    --↵
    -0.05
    unkt
    -0.05
    303
    -0.05
    qty
    -0.05
    POSITIVE LOGITS
     cabinet
    0.07
     �
    0.07
     меч
    0.07
     mehr
    0.07
     เ�
    0.07
     بازار
    0.07
    short
    0.07
    asier
    0.06
     Numer
    0.06
     scrap
    0.06
    Act Density 0.001%

    No Known Activations