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

    Neuronpedia

    INDEX
    Explanations

    Property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elapsed
    -0.07
     SEM
    -0.06
     Chung
    -0.06
     köz
    -0.06
    _CIPHER
    -0.06
     Vic
    -0.06
     صرف
    -0.06
     Gun
    -0.06
     GÜ
    -0.06
     Cad
    -0.06
    POSITIVE LOGITS
    Property
    0.08
    Direction
    0.07
    ений
    0.06
     FileInfo
    0.06
    鲜
    0.06
    _positions
    0.06
     importing
    0.06
    posables
    0.06
     refuses
    0.06
    ]("
    0.06
    Act Density 0.001%

    No Known Activations