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
    串
    -0.07
    Robert
    -0.07
    朗
    -0.06
    Ν
    -0.06
    なた
    -0.06
    莱
    -0.06
    .students
    -0.06
    ─
    -0.06
    اپ
    -0.06
     función
    -0.06
    POSITIVE LOGITS
     flew
    0.06
    _den
    0.06
    .aggregate
    0.06
    _sign
    0.06
    .XPATH
    0.06
    (helper
    0.06
    (Register
    0.06
    ScrollView
    0.06
     Sel
    0.06
    Important
    0.06
    Act Density 0.215%

    No Known Activations