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

    Neuronpedia

    INDEX
    Explanations

    REST controller or API endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IA
    0.80
    LA
    0.68
    AK
    0.68
    SSD
    0.66
    ILL
    0.65
    IN
    0.64
    ES
    0.64
    ANG
    0.63
    ARA
    0.63
     храм
    0.62
    POSITIVE LOGITS
    ization
    0.66
    an
    0.66
    ation
    0.65
    ?
    0.64
    that
    0.63
    *
    0.61
    จาก
    0.61
    ing
    0.60
    (
    0.59
    <h2>
    0.56
    Act Density 0.000%

    No Known Activations