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

    Neuronpedia

    INDEX
    Explanations

    overall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enia
    -0.07
     destac
    -0.07
    Cho
    -0.07
     alleen
    -0.06
    KHTML
    -0.06
     semanas
    -0.06
    ynamodb
    -0.06
     mois
    -0.06
    stringLiteral
    -0.06
     weeks
    -0.06
    POSITIVE LOGITS
    サイズ
    0.06
     수행
    0.06
     DRV
    0.06
    .failure
    0.06
     reimburse
    0.06
     GT
    0.06
    .Adam
    0.06
    志
    0.06
     Rally
    0.06
     greatness
    0.06
    Act Density 0.018%

    No Known Activations