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

    Neuronpedia

    INDEX
    Explanations

    Inch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     опред
    -0.08
     возникнов
    -0.07
    _su
    -0.07
     violated
    -0.07
     statute
    -0.07
     выраж
    -0.07
     영향을
    -0.06
    ปฏ
    -0.06
     Scope
    -0.06
    |min
    -0.06
    POSITIVE LOGITS
    Chelsea
    0.06
    ‚ط
    0.06
    響
    0.06
     IG
    0.06
    ीं।
    0.06
    (audio
    0.06
    ,↵↵↵↵
    0.06
    arga
    0.06
     Civic
    0.05
    EntityType
    0.05
    Act Density 0.001%

    No Known Activations