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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кры
    -0.07
     METHOD
    -0.06
     illegally
    -0.06
     Joan
    -0.06
    StackTrace
    -0.06
    Snake
    -0.06
     deceive
    -0.06
     tmp
    -0.06
    851
    -0.06
    “How
    -0.06
    POSITIVE LOGITS
    setFlash
    0.07
     "-";↵
    0.06
     thuis
    0.06
     Fukushima
    0.06
     Eisen
    0.06
    >e
    0.06
    �情
    0.06
    นๆ
    0.06
    recision
    0.06
    +h
    0.06
    Act Density 0.022%

    No Known Activations