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

    Neuronpedia

    INDEX
    Explanations

    say "20" numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANY
    -0.07
    ули
    -0.07
    -Z
    -0.07
     naturally
    -0.06
    Kon
    -0.06
    vor
    -0.06
     fellowship
    -0.06
    gesch
    -0.06
     springs
    -0.06
     catholic
    -0.06
    POSITIVE LOGITS
    (Byte
    0.06
     responseType
    0.06
     کاربرد
    0.06
     zoals
    0.06
     Everest
    0.06
     入
    0.06
    _VF
    0.06
     cảnh
    0.06
    _FW
    0.06
     зменш
    0.06
    Act Density 0.003%

    No Known Activations