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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DanhMucSP
    0.27
    SRPI
    0.26
    鳃
    0.24
    calup
    0.24
    ্ন
    0.23
    RELATIVA
    0.23
    RELATES
    0.23
    バリー
    0.23
    ayutt
    0.23
    cccnc
    0.22
    POSITIVE LOGITS
     sistem
    0.26
     plugins
    0.25
     using
    0.25
     notifications
    0.25
     fichiers
    0.25
    2
    0.24
     and
    0.24
    up
    0.24
     ->
    0.24
     -
    0.24
    Act Density 0.097%

    No Known Activations