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

    Neuronpedia

    INDEX
    Explanations

    judgment may be entered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     passent
    0.40
     acu
    0.38
    Drawable
    0.38
     tumble
    0.38
     instantaneous
    0.38
    اداسی
    0.38
     adapters
    0.37
    measurable
    0.37
     precipitated
    0.36
     precipitation
    0.36
    POSITIVE LOGITS
     overturn
    0.75
     overturning
    0.72
     annul
    0.70
     revocation
    0.68
     overturned
    0.68
     anul
    0.68
     petition
    0.67
     review
    0.63
     Grounds
    0.62
     revoked
    0.61
    Act Density 0.005%

    No Known Activations