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

    Neuronpedia

    INDEX
    Explanations

    various types of code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.82
    haustible
    -0.81
     iſt
    -0.80
     Theſe
    -0.75
     وصلة
    -0.74
     BIBSYS
    -0.73
    Ингредиенты
    -0.72
     whoſe
    -0.71
     doubtnut
    -0.71
    Бахар
    -0.71
    POSITIVE LOGITS
    ↵
    0.67
      
    0.59
    ↵↵
    0.56
     :
    0.56
    Statics
    0.55
    .
    0.55
    D
    0.55
     This
    0.54
    ..
    0.54
    <strong>
    0.54
    Act Density 0.514%

    No Known Activations