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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NotFound
    -0.08
    金字塔
    -0.08
     Bloss
    -0.07
     dès
    -0.07
     make
    -0.07
    da
    -0.07
    於
    -0.07
    (rect
    -0.07
     бил
    -0.07
     European
    -0.06
    POSITIVE LOGITS
    HF
    0.07
     המשפ
    0.07
     blank
    0.07
    Submitting
    0.06
    检察机关
    0.06
     Tampa
    0.06
    oggle
    0.06
    $temp
    0.06
    ﮨ
    0.06
     heirs
    0.06
    Act Density 0.003%

    No Known Activations