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
     trời
    -0.07
     klu
    -0.06
     webpage
    -0.06
    >):
    -0.06
    _document
    -0.06
    _JS
    -0.06
     monstrous
    -0.06
    .rad
    -0.06
     forfeiture
    -0.06
     돌아
    -0.06
    POSITIVE LOGITS
     derby
    0.06
    irlines
    0.06
    	union
    0.06
     tion
    0.06
    /messages
    0.06
    $item
    0.06
    
    0.06
    اعب
    0.06
     různých
    0.06
    ricanes
    0.06
    Act Density 0.000%

    No Known Activations