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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ujemy
    -0.07
     severed
    -0.07
     {};↵
    -0.07
     slew
    -0.07
    ۰
    -0.07
     рав
    -0.07
    據
    -0.07
    Team
    -0.07
     gioc
    -0.06
     negatively
    -0.06
    POSITIVE LOGITS
    -point
    0.07
    거
    0.06
     underage
    0.06
     mantle
    0.06
    oint
    0.06
     frags
    0.06
     cassette
    0.06
    thritis
    0.06
     ود
    0.06
    -avatar
    0.06
    Act Density 0.028%

    No Known Activations