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

    Neuronpedia

    INDEX
    Explanations

    punctuation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duck
    -0.07
    liğe
    -0.06
    becca
    -0.06
    _POINT
    -0.06
    theid
    -0.06
    лено
    -0.06
    thro
    -0.06
    ↵
    -0.06
    feit
    -0.06
     cham
    -0.06
    POSITIVE LOGITS
     Benton
    0.07
    /p
    0.07
     vẫn
    0.07
     економ
    0.07
     グ
    0.06
     domains
    0.06
    /f
    0.06
     galer
    0.06
                    
    0.06
    (params
    0.06
    Act Density 0.000%

    No Known Activations