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

    Neuronpedia

    INDEX
    Explanations

    implies, un- prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moors
    0.83
     severity
    0.79
     Allie
    0.77
     Warner
    0.77
     JVM
    0.76
    ূল্যে
    0.76
     nipple
    0.75
    TNF
    0.75
    BAI
    0.73
     wrinkle
    0.72
    POSITIVE LOGITS
    ের
    0.63
    imized
    0.61
    amen
    0.61
    ifon
    0.60
     apresentado
    0.60
    ateg
    0.59
     douloureuse
    0.59
    রকম
    0.59
    DOL
    0.58
     дослід
    0.58
    Act Density 0.189%

    No Known Activations