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

    Neuronpedia

    INDEX
    Explanations

    bracketed numbered citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teme
    -0.09
    ignty
    -0.09
     rituals
    -0.08
    innamon
    -0.08
     ritual
    -0.08
    enar
    -0.08
    vaise
    -0.08
    nias
    -0.08
    ieri
    -0.08
    oca
    -0.08
    POSITIVE LOGITS
    编号
    0.12
     numbered
    0.12
     നമ്പ
    0.12
     번호
    0.12
    番号
    0.11
    번호
    0.11
     شماره
    0.11
    (index
    0.10
     નંબર
    0.10
     नंबर
    0.10
    Act Density 0.013%

    No Known Activations