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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    quantitative references or numerical values.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     쉽
    -0.06
     degraded
    -0.06
    чного
    -0.06
    meeting
    -0.06
    akh
    -0.06
    브
    -0.06
    ении
    -0.06
    -Д
    -0.06
    _SH
    -0.06
     김
    -0.06
    POSITIVE LOGITS
    Moment
    0.07
     말을
    0.07
     inspirational
    0.07
    toArray
    0.06
    .Toggle
    0.06
     Albums
    0.06
     aconte
    0.06
    .";
    0.06
     beat
    0.06
    Accept
    0.06
    Act Density 0.041%

    No Known Activations