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

    Neuronpedia

    INDEX
    Explanations

    Provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Congress
    -0.08
     Congressional
    -0.08
    (Storage
    -0.08
     حال
    -0.08
     Congress
    -0.08
    Detected
    -0.08
     dictator
    -0.08
    subjects
    -0.08
    ↵				↵
    -0.08
    :")↵
    -0.07
    POSITIVE LOGITS
     importantly
    0.09
     тщательно
    0.09
     concise
    0.09
     estre
    0.08
    ครบ
    0.08
     எழ
    0.08
     robust
    0.08
     thoroughly
    0.07
     gracefully
    0.07
     thorough
    0.07
    Act Density 0.123%

    No Known Activations