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

    Neuronpedia

    INDEX
    Explanations

    footer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _boost
    -0.08
    pose
    -0.07
     hình
    -0.07
    (Bitmap
    -0.07
     cam
    -0.07
    Cab
    -0.06
    招募
    -0.06
    (sizeof
    -0.06
     стал
    -0.06
    _Version
    -0.06
    POSITIVE LOGITS
    🐙
    0.08
     FileSystem
    0.07
    衲
    0.07
    INS
    0.07
    这些问题
    0.07
    smtp
    0.07
    实在是
    0.07
    ⋰
    0.07
    accur
    0.07
    并不会
    0.07
    Act Density 0.001%

    No Known Activations