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

    Neuronpedia

    INDEX
    Explanations

    code and mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INLINE
    -0.06
    はじめ
    -0.06
    lion
    -0.06
     winner
    -0.06
     Ge
    -0.06
    镧
    -0.06
    泂
    -0.06
    не
    -0.06
    nota
    -0.06
     fancy
    -0.06
    POSITIVE LOGITS
    .Enc
    0.08
    �
    0.07
     camps
    0.07
     discs
    0.07
    _Display
    0.07
     Crom
    0.07
     pamph
    0.07
     totals
    0.07
     Pers
    0.07
    .impl
    0.07
    Act Density 0.065%

    No Known Activations