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

    Neuronpedia

    INDEX
    Explanations

    school

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    burg
    -0.07
    OPER
    -0.07
    iid
    -0.07
    _purchase
    -0.07
     urb
    -0.07
    いただける
    -0.07
    express
    -0.07
    ynamic
    -0.07
    -be
    -0.07
     offering
    -0.06
    POSITIVE LOGITS
    枪
    0.08
    高等学校
    0.07
    โคร
    0.07
    _slots
    0.07
    ॱ
    0.06
     slot
    0.06
     trường
    0.06
    /ay
    0.06
    (datos
    0.06
    .compiler
    0.06
    Act Density 0.035%

    No Known Activations