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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dart
    -0.08
    Sele
    -0.07
    留守
    -0.07
     Erl
    -0.07
    Clone
    -0.07
     Zus
    -0.07
     cheers
    -0.07
     sometime
    -0.06
     getImage
    -0.06
    mj
    -0.06
    POSITIVE LOGITS
    _request
    0.07
    卬
    0.07
    业态
    0.06
     уникальн
    0.06
    _ioctl
    0.06
    _Print
    0.06
    台账
    0.06
     hoc
    0.06
    宏大
    0.06
    _-
    0.06
    Act Density 0.078%

    No Known Activations