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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Juni
    -0.07
    Uno
    -0.07
    提示
    -0.07
     bian
    -0.06
     tack
    -0.06
     dass
    -0.06
    Latch
    -0.06
     iPod
    -0.06
    	actual
    -0.06
     ram
    -0.06
    POSITIVE LOGITS
     Le
    0.07
    Making
    0.07
     {*}
    0.07
     할
    0.07
    ᕚ
    0.07
    hip
    0.07
    公立医院
    0.07
    Military
    0.07
    _blueprint
    0.07
    VISIBLE
    0.07
    Act Density 0.104%

    No Known Activations