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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ).
    -0.06
    ':['
    -0.06
     ():
    -0.06
     wording
    -0.06
    ]).
    -0.06
    $product
    -0.06
     توص
    -0.06
    Multiply
    -0.06
     ().
    -0.06
     اما
    -0.06
    POSITIVE LOGITS
     screenSize
    0.07
    �
    0.07
     Aspen
    0.06
    ứ
    0.06
    DataSet
    0.06
     �
    0.06
    Exec
    0.06
    uzzer
    0.06
    reen
    0.06
    롤
    0.06
    Act Density 0.002%

    No Known Activations