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

    Neuronpedia

    INDEX
    Explanations

    cyberpunk portraits, streets, and cityscapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.59
    into
    0.57
    key
    0.54
    with
    0.54
    at
    0.54
    if
    0.53
    ed
    0.52
    to
    0.52
     three
    0.52
     two
    0.51
    POSITIVE LOGITS
     أو
    0.62
     الأ
    0.59
     א
    0.58
    ۔
    0.57
     వ్యక్
    0.56
     زنان
    0.56
     افراد
    0.55
     או
    0.54
     adultos
    0.54
     أ
    0.54
    Act Density 0.001%

    No Known Activations