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

    Neuronpedia

    INDEX
    Explanations

    competition or game show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     computed
    0.47
     perfused
    0.42
    元
    0.39
    ฬ
    0.39
    iot
    0.39
     escaping
    0.39
    ຫມ
    0.39
     fever
    0.39
     ü
    0.38
     computes
    0.38
    POSITIVE LOGITS
    եք
    0.43
    ния
    0.42
    Leary
    0.42
     trial
    0.42
    proven
    0.41
    Trial
    0.40
    Strike
    0.40
    Proven
    0.40
     कारी
    0.39
    trial
    0.39
    Act Density 0.001%

    No Known Activations