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

    Neuronpedia

    INDEX
    Explanations

    mathematical analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쿙
    -0.07
     Rather
    -0.07
     Massachusetts
    -0.07
    .skip
    -0.07
    apse
    -0.07
    抑え
    -0.07
    (game
    -0.06
    例外
    -0.06
    一点也不
    -0.06
    ﳕ
    -0.06
    POSITIVE LOGITS
    ᵘ
    0.07
    ]+\
    0.07
     אלקטרוני
    0.07
    مدن
    0.07
    latex
    0.06
     videot
    0.06
    (write
    0.06
     mascara
    0.06
    �
    0.06
     campaña
    0.06
    Act Density 0.006%

    No Known Activations