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

    Neuronpedia

    INDEX
    Explanations

    product availability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jual
    -0.07
     uveden
    -0.07
    на
    -0.06
     Floyd
    -0.06
    Click
    -0.06
    Article
    -0.06
    `);↵
    -0.06
    ροφορ
    -0.06
    mod
    -0.06
     Asian
    -0.06
    POSITIVE LOGITS
     nause
    0.06
    нут
    0.06
     travelling
    0.06
    (non
    0.06
    าศ
    0.06
     plais
    0.06
     rencontre
    0.06
     Kỳ
    0.06
    İs
    0.06
     Jin
    0.05
    Act Density 0.058%

    No Known Activations