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
    ­s
    -0.07
                            ↵
    -0.07
     puppies
    -0.07
    ­n
    -0.06
    _TOUCH
    -0.06
    -0.06
     sisters
    -0.06
    \")
    -0.06
    Adult
    -0.06
    Psych
    -0.06
    POSITIVE LOGITS
     хроничес
    0.07
    olicited
    0.06
     интерес
    0.06
     Jamal
    0.06
     Barcl
    0.06
    ublice
    0.06
     Sentence
    0.06
    .MinValue
    0.06
     calend
    0.06
    戒
    0.06
    Act Density 0.062%

    No Known Activations