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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _signal
    -0.07
    .twimg
    -0.07
     illumination
    -0.06
     activity
    -0.06
     Station
    -0.06
    ingroup
    -0.06
     instructions
    -0.06
    戦
    -0.06
     reaction
    -0.06
    .crt
    -0.06
    POSITIVE LOGITS
    'autres
    0.07
     anál
    0.07
     túi
    0.06
     Categoria
    0.06
     Slov
    0.06
    Normal
    0.06
    nan
    0.06
    ınd
    0.06
     eBay
    0.06
    ेयर
    0.06
    Act Density 4.105%

    No Known Activations