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

    Neuronpedia

    INDEX
    Explanations

    list items or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     необхідно
    0.48
     necesaria
    0.47
     мебель
    0.45
     chimique
    0.45
    ﻨ
    0.45
     Jó
    0.44
     nécessaire
    0.44
     необходимость
    0.44
    蒻
    0.43
     necessidade
    0.42
    POSITIVE LOGITS
    traces
    0.46
    aggers
    0.45
     traces
    0.45
    p
    0.44
     amusing
    0.44
    olič
    0.44
    trace
    0.43
    ured
    0.43
    adb
    0.43
     unfold
    0.42
    Act Density 0.004%

    No Known Activations