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

    Neuronpedia

    INDEX
    Explanations

    legal/business publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     për
    -0.08
    واس
    -0.07
     Gross
    -0.07
    뱔
    -0.07
     hackers
    -0.07
    מז
    -0.07
     Förder
    -0.06
    พรรณ
    -0.06
    瀛
    -0.06
    忡
    -0.06
    POSITIVE LOGITS
     TABLE
    0.08
     relief
    0.07
    专业的
    0.07
    _bo
    0.07
    שירה
    0.07
    女排
    0.07
     piping
    0.07
    READING
    0.07
    عظيم
    0.07
     redirection
    0.07
    Act Density 0.007%

    No Known Activations