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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لكن
    0.46
    ađ
    0.41
    ເຮັດ
    0.41
    𝓮
    0.40
    гід
    0.40
    getBook
    0.39
     አይደ
    0.38
     ligados
    0.38
    ه
    0.38
    spiderX
    0.38
    POSITIVE LOGITS
    1
    0.52
    0
    0.44
    (
    0.42
    <0x80>
    0.38
     was
    0.36
     .
    0.36
     the
    0.36
     a
    0.35
     be
    0.35
    ong
    0.33
    Act Density 0.015%

    No Known Activations