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

    Neuronpedia

    INDEX
    Explanations

    synthesis and sophistication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rows
    0.45
    asgi
    0.43
     الانتق
    0.42
     Provisions
    0.41
     teleport
    0.41
    oslovens
    0.40
    ungkinkan
    0.40
     রাজনৈতিক
    0.40
     protests
    0.39
     walkable
    0.39
    POSITIVE LOGITS
    IMI
    0.48
    MD
    0.47
    PP
    0.46
    NO
    0.46
    เอ
    0.46
    CD
    0.46
    IF
    0.45
    ATI
    0.45
    OSH
    0.45
    TM
    0.44
    Act Density 0.001%

    No Known Activations