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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    culture
    -0.07
     suchen
    -0.07
    ($
    -0.07
    大切な
    -0.07
     join
    -0.07
    最小
    -0.06
    obsług
    -0.06
    imetype
    -0.06
     lie
    -0.06
    หมาย
    -0.06
    POSITIVE LOGITS
     Sidney
    0.07
    urret
    0.07
    pane
    0.07
    器材
    0.07
     Showcase
    0.07
    SplitOptions
    0.07
    骸
    0.07
    .getParam
    0.07
    电气
    0.07
     hydr
    0.07
    Act Density 0.256%

    No Known Activations