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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or groups that are being evaluated or discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "that" or "those"

    np_acts-logits-general · gemini-2.0-flash

    those plural nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.70
    ::*;
    -0.64
    ensement
    -0.52
    IndentedString
    -0.51
     démarche
    -0.51
    lateur
    -0.49
    IConfiguration
    -0.48
     ezért
    -0.47
    ChildScrollView
    -0.46
    addAction
    -0.45
    POSITIVE LOGITS
     that
    0.93
     who
    0.71
    jenige
    0.70
    enumi
    0.70
    jenigen
    0.70
    ⓧ
    0.69
    genen
    0.68
    ValueStyle
    0.66
    ที่
    0.65
    IBOutlet
    0.62
    Act Density 0.151%

    No Known Activations