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

    Neuronpedia

    INDEX
    Explanations

    comfort levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Allow
    0.52
     כאשר
    0.48
    Employ
    0.46
     omdat
    0.46
     क्योंकि
    0.46
     använda
    0.46
    ;</
    0.45
    Wenn
    0.44
     사용하는
    0.44
     gewährleisten
    0.43
    POSITIVE LOGITS
     becomes
    0.98
     gets
    0.92
     goes
    0.82
     disappears
    0.80
     became
    0.80
     become
    0.76
     begins
    0.72
     comes
    0.72
     vanishes
    0.70
     explodes
    0.70
    Act Density 0.561%

    No Known Activations