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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     등장
    -0.08
     πολι
    -0.08
    aturity
    -0.08
     업체
    -0.08
     Bankruptcy
    -0.07
     eingef
    -0.07
     дил
    -0.07
     {

↵
    -0.07
    NEL
    -0.07
    verters
    -0.07
    POSITIVE LOGITS
     recommandé
    0.10
     recomendado
    0.09
    .mount
    0.08
     voluntary
    0.08
     litro
    0.08
     recommended
    0.08
     intake
    0.08
     naast
    0.08
     consci
    0.08
    recommended
    0.08
    Act Density 0.003%

    No Known Activations