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
     BITS
    -0.07
    DockControl
    -0.06
     tisk
    -0.06
     لف
    -0.06
    .orders
    -0.06
    ReceiveMemoryWarning
    -0.06
    好き
    -0.06
    анных
    -0.06
    This
    -0.06
     honeymoon
    -0.06
    POSITIVE LOGITS
     successful
    0.07
     locally
    0.06
     musician
    0.06
     evaluating
    0.06
     optimal
    0.06
    	cc
    0.06
     muted
    0.06
     initData
    0.06
    american
    0.06
     bei
    0.06
    Act Density 0.016%

    No Known Activations