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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kcal
    -0.07
    _parameter
    -0.06
    _dept
    -0.06
    _dual
    -0.06
     cornerback
    -0.06
    );$
    -0.06
    ursos
    -0.06
    yy
    -0.06
    ^n
    -0.06
     moderator
    -0.06
    POSITIVE LOGITS
     должно
    0.07
    ullets
    0.06
    alogy
    0.06
    ''↵
    0.06
                         ↵
    0.06
     occas
    0.06
    �
    0.06
     خوب
    0.06
    міністра
    0.06
    weathermap
    0.06
    Act Density 0.002%

    No Known Activations