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

    Neuronpedia

    INDEX
    Explanations

    sparse data and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    žitě
    -0.07
    setImage
    -0.07
     amber
    -0.06
     getPath
    -0.06
     necessário
    -0.06
    amburger
    -0.06
    resa
    -0.06
     onTap
    -0.06
    needed
    -0.06
    obierno
    -0.06
    POSITIVE LOGITS
     punishment
    0.07
    AAAAAAAA
    0.06
    200
    0.06
    phyl
    0.06
     Ph
    0.06
    排
    0.06
     Readers
    0.06
    ophil
    0.06
     KR
    0.06
    偶
    0.06
    Act Density 0.011%

    No Known Activations