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

    Neuronpedia

    INDEX
    Explanations

    return empty or null

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जेव्हा
    0.32
    जब
    0.32
     TEMPERATURE
    0.31
     água
    0.30
     온도
    0.30
     ступен
    0.29
     максима
    0.29
     енер
    0.28
     жид
    0.28
     torre
    0.28
    POSITIVE LOGITS
    invalid
    0.38
    throw
    0.38
     unable
    0.37
    alert
    0.37
    unable
    0.35
    failed
    0.34
    řejmě
    0.33
     couldn
    0.32
    warning
    0.32
    怅
    0.32
    Act Density 0.231%

    No Known Activations