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
    hydr
    -0.07
    设置了
    -0.07
    ylvania
    -0.07
     הו
    -0.07
     ذو
    -0.07
     análisis
    -0.07
    seudo
    -0.06
    劣势
    -0.06
     frau
    -0.06
     huh
    -0.06
    POSITIVE LOGITS
    `.
    0.07
     learn
    0.07
    ,arr
    0.07
    credentials
    0.07
     Palin
    0.07
    رين
    0.07
    .isDebugEnabled
    0.07
    ☑
    0.07
    رغب
    0.06
    ernen
    0.06
    Act Density 0.006%

    No Known Activations