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

    Neuronpedia

    INDEX
    Explanations

    impressive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    birds
    -0.06
    boat
    -0.06
     ()↵
    -0.06
    žila
    -0.06
     cult
    -0.06
    aket
    -0.06
     belts
    -0.06
    _widgets
    -0.06
    Actualizar
    -0.06
    -fold
    -0.06
    POSITIVE LOGITS
     impressive
    0.11
     приг
    0.07
    appid
    0.07
     formidable
    0.07
    考
    0.07
     prowess
    0.07
    0.07
     XXX
    0.07
     εμφ
    0.07
    驚
    0.07
    Act Density 0.006%

    No Known Activations