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

    Neuronpedia

    INDEX
    Explanations

    phrases related to familial or community connections and interactions

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

    all that, any eyes, of mine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hoeddwyd
    -0.48
    monia
    -0.38
    ificato
    -0.38
    IFont
    -0.37
     поступа
    -0.37
    PositiveButton
    -0.37
    osp
    -0.36
    zzleHttp
    -0.36
     Bett
    -0.35
    itoria
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.63
    parsedMessage
    0.51
    最快更新
    0.49
    +#+
    0.46
    attendre
    0.46
    şört
    0.45
     loves
    0.44
     للمعارف
    0.43
    Erstellt
    0.41
    UnknownFields
    0.41
    Act Density 0.001%

    No Known Activations