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

    Neuronpedia

    INDEX
    Explanations

    appeals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leet
    -0.07
    Made
    -0.07
     ฟร
    -0.06
     bud
    -0.06
     mon
    -0.06
    Mix
    -0.06
    内
    -0.06
     жит
    -0.06
    (cc
    -0.06
     그는
    -0.06
    POSITIVE LOGITS
     szer
    0.07
    _ALT
    0.07
    UniqueId
    0.06
    _Null
    0.06
           ↵↵
    0.06
    ruž
    0.06
    Angular
    0.06
    .readAs
    0.06
    -pos
    0.06
    ตล
    0.06
    Act Density 0.002%

    No Known Activations