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

    Neuronpedia

    INDEX
    Explanations

    Numeral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buffered
    -0.06
    ziej
    -0.06
     Randall
    -0.06
     outsourcing
    -0.06
     disclose
    -0.06
     disclosed
    -0.06
    mqtt
    -0.06
    Initially
    -0.06
     tratt
    -0.06
    Ix
    -0.06
    POSITIVE LOGITS
     accom
    0.07
    .gson
    0.07
     ETF
    0.07
    _market
    0.07
     minLength
    0.06
    編
    0.06
     �
    0.06
     SEA
    0.06
    .jwt
    0.06
    自
    0.06
    Act Density 0.006%

    No Known Activations