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

    Neuronpedia

    INDEX
    Explanations

    Summer Olympics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ospheric
    0.49
    urb
    0.47
    ’
    0.46
    obile
    0.44
    铧
    0.44
    rupt
    0.43
    cre
    0.42
    hedral
    0.42
    izing
    0.42
    warf
    0.42
    POSITIVE LOGITS
     நியூ
    0.66
     kindergarten
    0.60
     immunized
    0.60
     warum
    0.58
     Второй
    0.57
     capital
    0.55
     अत्या
    0.55
     responsável
    0.55
     كمان
    0.55
     Нью
    0.55
    Act Density 0.000%

    No Known Activations