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

    Neuronpedia

    INDEX
    Explanations

    body composition changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bombard
    0.59
     feud
    0.59
     পাকিস্ত
    0.58
     informe
    0.57
     فرنسا
    0.57
     pusieron
    0.57
    classList
    0.56
    景象
    0.56
     incendi
    0.55
    肌肤
    0.55
    POSITIVE LOGITS
    in
    0.93
    u
    0.86
    en
    0.80
    a
    0.71
    as
    0.70
    an
    0.70
    o
    0.69
    of
    0.66
    inį
    0.66
    r
    0.64
    Act Density 0.001%

    No Known Activations