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

    Neuronpedia

    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aş
    -0.08
    ρός
    -0.07
     Sponge
    -0.07
     역시
    -0.07
    deposit
    -0.06
     instal
    -0.06
    itud
    -0.06
    poz
    -0.06
     #$
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    "}↵
    0.07
     Median
    0.06
     상황
    0.06
     terrorists
    0.06
     markup
    0.06
    โทร
    0.06
     Anatomy
    0.06
     تع
    0.06
     Slice
    0.06
     Huyện
    0.06
    Act Density 0.000%

    No Known Activations