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

    Neuronpedia

    INDEX
    Explanations

    Clarence, clearance, Leung, glance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     플
    0.43
     squir
    0.42
     flags
    0.40
    ijo
    0.39
    コの
    0.39
     الحاس
    0.39
     фла
    0.38
     spéciale
    0.38
     presque
    0.38
     clubs
    0.37
    POSITIVE LOGITS
    ujen
    0.39
     exactly
    0.36
    exactly
    0.35
    few
    0.35
    PropertySheets
    0.35
    respectively
    0.34
     Julius
    0.34
    Few
    0.34
     Julio
    0.34
    ssen
    0.33
    Act Density 0.000%

    No Known Activations