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

    Neuronpedia

    INDEX
    Explanations

    formulas and variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specialized
    -0.08
     unsure
    -0.07
     altid
    -0.07
     properly
    -0.07
     eager
    -0.07
     uncertain
    -0.07
     Overflow
    -0.07
     Kov
    -0.07
     bouncing
    -0.07
     Erste
    -0.07
    POSITIVE LOGITS
    Validator
    0.10
    _VECTOR
    0.09
     দেখে
    0.09
    جاه
    0.08
     забуд
    0.08
    .validators
    0.08
    .party
    0.08
     তদন্ত
    0.08
    セル
    0.08
    	file
    0.08
    Act Density 0.026%

    No Known Activations