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

    Neuronpedia

    INDEX
    Explanations

    request, views, status, confirm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nk
    0.38
    ryn
    0.37
    ลิ
    0.36
     вопро
    0.36
     vra
    0.36
     ښ
    0.35
     osv
    0.35
     कंप
    0.34
    websites
    0.34
    rails
    0.34
    POSITIVE LOGITS
    Formats
    0.48
     formats
    0.41
     notice
    0.39
     PJ
    0.39
     COLE
    0.39
    Ꮄ
    0.39
     status
    0.38
    PJ
    0.38
    formats
    0.37
    GLUT
    0.37
    Act Density 0.000%

    No Known Activations