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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caste
    -0.07
     Hungarian
    -0.06
     vídeo
    -0.06
    (font
    -0.06
    adas
    -0.06
     RADIO
    -0.06
     Ireland
    -0.06
     blanks
    -0.06
    ADOW
    -0.06
     OFFSET
    -0.06
    POSITIVE LOGITS
    -param
    0.08
    -N
    0.07
    lename
    0.07
    洁
    0.07
    setError
    0.06
    _entropy
    0.06
    namen
    0.06
     adicion
    0.06
    為
    0.06
    .Flush
    0.06
    Act Density 0.046%

    No Known Activations