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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    23
    -0.07
    aed
    -0.07
    gel
    -0.06
     dance
    -0.06
    ヶ月
    -0.06
     confines
    -0.06
     members
    -0.06
     color
    -0.06
    40
    -0.06
     draw
    -0.06
    POSITIVE LOGITS
    ResponseType
    0.07
    んな
    0.06
    ("..
    0.06
    /T
    0.06
    unication
    0.06
     \"
    0.06
    Revenue
    0.06
    /f
    0.06
     Disposable
    0.06
     initialValue
    0.06
    Act Density 0.004%

    No Known Activations