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

    Neuronpedia

    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нями
    -0.08
    assin
    -0.08
     chamada
    -0.08
     μορ
    -0.08
     schizoph
    -0.08
     называ
    -0.08
     chamado
    -0.07
    炸
    -0.07
    idente
    -0.07
     graffiti
    -0.07
    POSITIVE LOGITS
     produce
    0.08
     major
    0.07
    _Read
    0.07
     dream
    0.07
     UK's
    0.07
     start
    0.07
     {
↵
    0.07
    _man
    0.07
     байланысты
    0.07
     blah
    0.07
    Act Density 0.009%

    No Known Activations