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

    Neuronpedia

    INDEX
    Explanations

    general discourse markers and punctuation within reviews

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.63
    ="@+
    -0.61
     Jinping
    -0.50
     CHtml
    -0.50
    stateProvider
    -0.48
    bliž
    -0.48
    ffindor
    -0.47
     Phari
    -0.47
     aceto
    -0.47
    rfloor
    -0.46
    POSITIVE LOGITS
    Portale
    0.68
    脚注の使い方
    0.61
    ifax
    0.59
    perf
    0.58
     חיצוניים
    0.57
     Each
    0.54
    FormTagHelper
    0.53
    //</
    0.51
    VersionUID
    0.50
     fédé
    0.50
    Act Density 1.952%

    No Known Activations