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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。（
    -0.06
     cloned
    -0.06
    ्थ
    -0.06
     landsc
    -0.06
    (dir
    -0.06
    하자
    -0.06
    .Some
    -0.06
    _full
    -0.06
    appendChild
    -0.06
    、三
    -0.05
    POSITIVE LOGITS
     cheaper
    0.06
    Fn
    0.06
    _id
    0.06
     Week
    0.06
    _CREATE
    0.06
     regimes
    0.06
    кого
    0.06
    WARD
    0.06
    <Renderer
    0.06
    ('
    0.06
    Act Density 0.011%

    No Known Activations