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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bbe
    -0.07
     Riv
    -0.07
    (Layout
    -0.07
     squad
    -0.06
     inve
    -0.06
     Tx
    -0.06
     Migration
    -0.06
     sporting
    -0.06
     faded
    -0.06
    drv
    -0.06
    POSITIVE LOGITS
    овани
    0.06
    字
    0.06
    .vue
    0.06
    Bro
    0.06
    year
    0.06
    $/)
    0.06
    מ
    0.06
    (Func
    0.06
    _FREQ
    0.06
    //↵↵↵
    0.06
    Act Density 0.003%

    No Known Activations