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

    Neuronpedia

    INDEX
    Explanations

    HTML id attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    1.02
    isms
    0.88
    ının
    0.71
    s
    0.71
    ants
    0.70
    ulas
    0.70
    ς
    0.70
     had
    0.69
    িকে
    0.68
    '
    0.67
    POSITIVE LOGITS
    to
    0.89
    the
    0.73
    l
    0.71
    Allora
    0.69
    M
    0.65
    Hold
    0.60
    ना
    0.60
    ِّف
    0.60
    RO
    0.59
     QVector
    0.59
    Act Density 0.008%

    No Known Activations