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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clip
    -0.07
    以
    -0.06
     scopes
    -0.06
     TOTAL
    -0.06
     colour
    -0.06
     showers
    -0.06
    用于
    -0.06
    rones
    -0.06
    il
    -0.06
    Holy
    -0.06
    POSITIVE LOGITS
     when
    0.09
    When
    0.07
     When
    0.07
     физ
    0.07
     WHEN
    0.07
    _codegen
    0.06
    "fmt
    0.06
    abbreviation
    0.06
     discrimin
    0.06
    .Guna
    0.06
    Act Density 0.059%

    No Known Activations