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

    Neuronpedia

    INDEX
    Explanations

    harmful versus harmless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tra
    2.23
     READ
    2.18
    hene
    2.16
    ധി
    2.13
    od
    2.13
    UTION
    2.07
     human
    2.07
     CUT
    2.05
     रामपुर
    2.04
     root
    2.04
    POSITIVE LOGITS
    izontal
    3.55
    ክምና
    3.14
    ằng
    3.05
     indexRouter
    3.02
    成像
    2.98
    Ꮳ
    2.95
    adecimal
    2.91
    疸
    2.90
    unehmen
    2.86
    燡
    2.85
    Act Density 1.735%

    No Known Activations