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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    611
    -0.07
    legalArgumentException
    -0.06
    .bo
    -0.06
     wichtig
    -0.06
    葉
    -0.06
    _DE
    -0.06
    (ir
    -0.06
    .Activity
    -0.06
     мног
    -0.06
    	ac
    -0.06
    POSITIVE LOGITS
    fastcall
    0.07
     активно
    0.06
     yoktur
    0.06
     повед
    0.06
    Verbose
    0.06
    _fig
    0.06
    (grammarAccess
    0.06
    ُّ
    0.06
     conveniently
    0.06
     transition
    0.06
    Act Density 0.014%

    No Known Activations