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
     uniquely
    -0.07
    	distance
    -0.07
    (_("
    -0.06
    _ori
    -0.06
    他の
    -0.06
    -0.06
     QFile
    -0.06
    Bank
    -0.06
     Zum
    -0.06
     Zur
    -0.06
    POSITIVE LOGITS
    _launcher
    0.08
     ورد
    0.06
    ез
    0.06
    stile
    0.06
    .sun
    0.06
     mund
    0.06
     Italia
    0.06
     pepp
    0.06
     Explosion
    0.06
    /port
    0.06
    Act Density 0.014%

    No Known Activations