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
     få
    -0.07
    cling
    -0.07
    <V
    -0.06
    preferences
    -0.06
    ánchez
    -0.06
     tvb
    -0.06
     Agile
    -0.06
     선거
    -0.06
    /apache
    -0.06
     flooring
    -0.06
    POSITIVE LOGITS
     prepend
    0.07
    gm
    0.07
     CART
    0.07
     olmasına
    0.06
    bro
    0.06
     SPR
    0.06
    
    0.06
    .Down
    0.06
    .Att
    0.06
    料無料
    0.06
    Act Density 0.055%

    No Known Activations