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

    Neuronpedia

    INDEX
    Explanations

    code snippets and raw text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imir
    -0.06
    serie
    -0.06
     teachers
    -0.06
    theless
    -0.06
    ALTH
    -0.06
     blamed
    -0.06
    px
    -0.06
    BOUND
    -0.06
    Op
    -0.06
     station
    -0.06
    POSITIVE LOGITS
     هش
    0.07
    Dialogue
    0.06
    956
    0.06
    -Jul
    0.06
     تز
    0.06
     goggles
    0.06
    ovaná
    0.06
    _rm
    0.06
    PerPage
    0.06
    にする
    0.06
    Act Density 0.000%

    No Known Activations