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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lacks
    -0.07
     tslib
    -0.07
     osobní
    -0.06
    |l
    -0.06
    tx
    -0.06
    _ATTRIBUTES
    -0.06
     bankers
    -0.06
     с
    -0.06
    	LP
    -0.06
     小
    -0.06
    POSITIVE LOGITS
     влас
    0.06
    alaria
    0.06
    =".$
    0.06
    exter
    0.06
    stripe
    0.06
    ======
    0.06
     terminals
    0.06
    地址
    0.06
     اه
    0.06
     voz
    0.06
    Act Density 0.061%

    No Known Activations