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

    Neuronpedia

    INDEX
    Explanations

    progress bar duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carol
    0.46
    ySpeed
    0.42
    嫚
    0.42
     मालिनी
    0.39
    🪜
    0.39
     BGPS
    0.38
    อาด
    0.38
    ंजनों
    0.38
    ើញ
    0.38
    𝓖
    0.38
    POSITIVE LOGITS
     total
    0.73
     currentTime
    0.69
    currentTime
    0.66
    total
    0.65
     Time
    0.64
     time
    0.63
     Duration
    0.62
     remaining
    0.62
     duration
    0.61
     Total
    0.61
    Act Density 0.000%

    No Known Activations