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

    Neuronpedia

    INDEX
    Explanations

    book titles and publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.52
    Ī
    0.47
    ,
    0.44
    _
    0.39
    /
    0.36
     Pusat
    0.35
    .
    0.35
    )|
    0.35
    "
    0.34
    )
    0.34
    POSITIVE LOGITS
    <unused1861>
    0.46
    <unused1868>
    0.45
    <unused664>
    0.45
    зили
    0.45
    ቨ
    0.45
     গঙ্গ
    0.44
    <unused616>
    0.44
    <unused524>
    0.43
    <unused2067>
    0.43
    ն
    0.43
    Act Density 0.000%

    No Known Activations