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

    Neuronpedia

    INDEX
    Explanations

    code comments and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     التص
    -0.79
    域名
    -0.74
    pte
    -0.72
    \",\
    -0.71
     defaultstate
    -0.68
     Ingo
    -0.66
    ENCODING
    -0.66
     panting
    -0.65
    ace
    -0.64
    AUTO
    -0.64
    POSITIVE LOGITS
     lip
    0.69
    bland
    0.69
     będzie
    0.69
    IPH
    0.68
    ciudad
    0.68
    fazer
    0.66
    voce
    0.66
    forestry
    0.66
     Roosevelt
    0.66
    cidade
    0.66
    Act Density 0.058%

    No Known Activations