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

    Neuronpedia

    INDEX
    Explanations

    Large Language Models, Support Vector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     süre
    0.39
     кризи
    0.38
     atleast
    0.37
     灬
    0.37
    rection
    0.36
     やつ
    0.36
    OCKET
    0.36
    डक्शन
    0.36
     സമയം
    0.36
    INDOW
    0.35
    POSITIVE LOGITS
     The
    0.40
    <0xF0>
    0.38
     (
    0.38
     Sauvignon
    0.37
    U
    0.36
    -
    0.36
     teknologi
    0.36
     U
    0.35
    ('
    0.35
    _
    0.35
    Act Density 0.175%

    No Known Activations