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

    Neuronpedia

    INDEX
    Explanations

    chemical elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Qty
    -0.06
     reliance
    -0.06
     defiance
    -0.06
    ัตน
    -0.06
     Dread
    -0.06
     Qin
    -0.06
     Naughty
    -0.06
     Switch
    -0.06
    .buf
    -0.06
    oscope
    -0.06
    POSITIVE LOGITS
     obe
    0.07
    νη
    0.07
     companions
    0.06
    704
    0.06
     sight
    0.06
    Observ
    0.06
    prehensive
    0.06
    ्रव
    0.06
     memorable
    0.06
    _home
    0.06
    Act Density 0.001%

    No Known Activations