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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    きた
    -0.07
     enslaved
    -0.07
     templ
    -0.06
    _REFER
    -0.06
    λλά
    -0.06
    (this
    -0.06
     عم
    -0.06
    sta
    -0.06
    _Time
    -0.06
    @return
    -0.06
    POSITIVE LOGITS
    RESET
    0.07
     precip
    0.07
     Divine
    0.06
     lexical
    0.06
     suppress
    0.06
     negotiated
    0.06
    awan
    0.06
     ноября
    0.06
     GAR
    0.06
     UNIQUE
    0.06
    Act Density 0.018%

    No Known Activations