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

    Neuronpedia

    INDEX
    Explanations

    Che

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ダメ
    -0.07
    栲
    -0.07
     выб
    -0.07
     destruct
    -0.07
    碳酸
    -0.07
    (PropertyName
    -0.07
     veröffent
    -0.07
     daddy
    -0.07
    砀
    -0.07
     Uran
    -0.06
    POSITIVE LOGITS
     Carlo
    0.07
     picnic
    0.07
    Piece
    0.07
     multiplied
    0.07
    وغ
    0.07
    otope
    0.07
    —which
    0.06
    )b
    0.06
    ↵   ↵
    0.06
    فاع
    0.06
    Act Density 0.016%

    No Known Activations