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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     js
    -0.07
     FixedUpdate
    -0.07
    _AREA
    -0.06
     comment
    -0.06
     подраз
    -0.06
     Download
    -0.06
    987
    -0.06
     ==
    -0.06
     encoder
    -0.06
    ере
    -0.06
    POSITIVE LOGITS
     بالأ
    0.06
    ’aut
    0.06
     trest
    0.06
     gasoline
    0.06
    skému
    0.06
     mistakenly
    0.06
    (Position
    0.06
    **(
    0.06
     sounding
    0.06
    $options
    0.06
    Act Density 0.045%

    No Known Activations