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

    Neuronpedia

    INDEX
    Explanations

    BY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mun
    -0.07
     Erf
    -0.07
     امام
    -0.06
    ंश
    -0.06
    梦
    -0.06
     fueled
    -0.06
     北京
    -0.06
    少女
    -0.06
    第
    -0.06
    刺
    -0.06
    POSITIVE LOGITS
     logos
    0.07
     TS
    0.07
     ketogenic
    0.06
     downside
    0.06
    bh
    0.06
    (pdev
    0.06
     KA
    0.06
    _locked
    0.06
     comic
    0.06
    -account
    0.06
    Act Density 0.000%

    No Known Activations