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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (of
    -0.07
    (payload
    -0.07
     tableName
    -0.07
     setattr
    -0.06
     sw
    -0.06
    أك
    -0.06
     κατα
    -0.06
     Winchester
    -0.06
     Maximum
    -0.06
    awan
    -0.06
    POSITIVE LOGITS
    .CV
    0.06
    isme
    0.06
    チ
    0.06
     sử
    0.06
     شود
    0.06
    questions
    0.06
     البر
    0.06
    /screen
    0.06
     calidad
    0.06
    reate
    0.06
    Act Density 0.003%

    No Known Activations