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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ética
    -0.07
    Ư
    -0.06
    olini
    -0.06
     Numerous
    -0.06
    Gab
    -0.06
    ificar
    -0.06
    Deep
    -0.06
     ashamed
    -0.06
     Moh
    -0.06
    Correction
    -0.06
    POSITIVE LOGITS
    $field
    0.07
     výbě
    0.07
     مکان
    0.06
     breweries
    0.06
    _->
    0.06
    _jobs
    0.06
     donation
    0.06
     debts
    0.06
    lfw
    0.06
     Keeps
    0.06
    Act Density 0.602%

    No Known Activations