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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mMap
    -0.07
    牍
    -0.07
    คา
    -0.07
     ak
    -0.06
    夭
    -0.06
     pixmap
    -0.06
     рассматр
    -0.06
     compar
    -0.06
    侃
    -0.06
    /St
    -0.06
    POSITIVE LOGITS
     outlines
    0.07
    %",
    0.07
     Training
    0.07
     superintendent
    0.07
     [])
    0.07
    ᠨ
    0.06
    _cre
    0.06
     Electric
    0.06
     excess
    0.06
    ata
    0.06
    Act Density 0.003%

    No Known Activations