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

    Neuronpedia

    INDEX
    Explanations

    allowing accumulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    抵抗
    0.41
     घंटा
    0.38
    onResume
    0.38
    聶
    0.37
    മല്ല
    0.36
    стых
    0.36
    ิค
    0.36
    ளர்
    0.36
     সফদর
    0.36
    0.35
    POSITIVE LOGITS
    ყო
    0.41
     tips
    0.39
     trav
    0.38
     digits
    0.38
     H
    0.38
     orbits
    0.37
     strokes
    0.36
    ground
    0.36
     caregivers
    0.36
    profits
    0.35
    Act Density 0.001%

    No Known Activations