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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bold
    -0.07
     신규
    -0.06
     thrott
    -0.06
     etkin
    -0.06
    .MON
    -0.06
     ovar
    -0.06
    amping
    -0.06
     เบ
    -0.06
     Recru
    -0.06
     todo
    -0.05
    POSITIVE LOGITS
    rsa
    0.07
    teste
    0.07
    program
    0.07
    Meteor
    0.07
    grams
    0.06
    ssl
    0.06
    _Public
    0.06
     inputFile
    0.06
    ")
↵
↵
    0.06
    [start
    0.06
    Act Density 0.013%

    No Known Activations