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

    Neuronpedia

    INDEX
    Explanations

    FROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.62
    請繼續往下閱讀
    -0.53
    లాలు
    -0.47
     sagrada
    -0.46
    ellite
    -0.42
    stuhl
    -0.42
    "]/
    -0.42
    Tazama
    -0.41
     ferdig
    -0.41
     betweenstory
    -0.40
    POSITIVE LOGITS
    SequentialGroup
    0.68
    /*
    0.60
     Himself
    0.58
     متعلقه
    0.57
    DoubleQuotes
    0.56
    Rohy
    0.56
     виправивши
    0.54
    jani
    0.54
     himself
    0.54
    InputLabel
    0.53
    Act Density 0.005%

    No Known Activations