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

    Neuronpedia

    INDEX
    Explanations

    the word 'outcomes' along with any nearby words

    oai_token-act-pair · gemini-2.0-flash

    outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ſelf
    -0.63
     pleaſure
    -0.63
     rôles
    -0.61
     ect
    -0.60
     ERS
    -0.57
     ſtate
    -0.57
     itſelf
    -0.57
     $_"
    -0.56
    equip
    -0.56
     (\<
    -0.56
    POSITIVE LOGITS
     مرئيه
    0.97
    endpush
    0.94
    fjspx
    0.94
    findpost
    0.91
    mybatisplus
    0.88
    AddHtmlAttribute
    0.86
    endregion
    0.86
    AxisAlignment
    0.85
    TagMode
    0.84
    Personendaten
    0.83
    Act Density 1.564%

    No Known Activations