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

    Neuronpedia

    INDEX
    Explanations

    hash tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Italian
    -0.07
     Nun
    -0.07
     Silence
    -0.07
    quarters
    -0.07
    Fri
    -0.07
     remedy
    -0.06
     discovers
    -0.06
     disliked
    -0.06
    yard
    -0.06
    FRING
    -0.06
    POSITIVE LOGITS
    يج
    0.07
    -lang
    0.06
     apro
    0.06
    acak
    0.06
    (Target
    0.06
     польз
    0.06
    ellipsis
    0.06
     transc
    0.06
     Preis
    0.06
     дов
    0.06
    Act Density 0.021%

    No Known Activations