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

    Neuronpedia

    INDEX
    Explanations

    biological family and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.89
    OUS
    0.86
    OV
    0.84
    ется
    0.83
    deki
    0.80
    OST
    0.77
    ﺒ
    0.77
    EK
    0.75
    Been
    0.75
    Screenshot
    0.75
    POSITIVE LOGITS
    g
    1.02
     biological
    1.00
    '
    0.91
    ↵
    0.91
    i
    0.88
    ac
    0.88
    t
    0.86
    c
    0.85
     Biological
    0.84
    he
    0.84
    Act Density 0.007%

    No Known Activations