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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    uminum
    -0.07
     antennas
    -0.07
    anova
    -0.06
     alta
    -0.06
     البي
    -0.06
    紙
    -0.06
     keycode
    -0.06
     distr
    -0.06
     Equivalent
    -0.06
    POSITIVE LOGITS
    _STREAM
    0.07
    (sum
    0.06
    ework
    0.06
    ATOR
    0.06
    birth
    0.06
      ↵  ↵
    0.06
    장은
    0.06
     Δι
    0.06
     Ihrem
    0.06
     κα
    0.06
    Act Density 0.001%

    No Known Activations