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
    xffff
    -0.07
    єш
    -0.06
    115
    -0.06
     clave
    -0.06
    Lic
    -0.06
    iomanip
    -0.06
     Extreme
    -0.06
    "H
    -0.06
    _DELAY
    -0.06
     Philips
    -0.06
    POSITIVE LOGITS
    _symbols
    0.07
     CAD
    0.07
     lstm
    0.07
    	className
    0.07
    ologna
    0.07
    LLU
    0.07
    AJ
    0.07
     className
    0.06
     Bellev
    0.06
    经营
    0.06
    Act Density 0.016%

    No Known Activations