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

    Neuronpedia

    INDEX
    Explanations

    albums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onom
    -0.07
     기록
    -0.07
    ायक
    -0.06
    奶
    -0.06
     Ara
    -0.06
     ه
    -0.06
     SEG
    -0.06
     bearings
    -0.06
    hendis
    -0.06
     franch
    -0.06
    POSITIVE LOGITS
     endif
    0.07
     позволяет
    0.07
    RTC
    0.07
    uais
    0.06
     astrology
    0.06
     особливо
    0.06
     Fixes
    0.06
     <:
    0.06
    quals
    0.06
     Typically
    0.06
    Act Density 0.005%

    No Known Activations