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

    Neuronpedia

    INDEX
    Explanations

    activities and technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ր
    0.52
    сон
    0.52
    荣
    0.52
     heure
    0.51
     ancienne
    0.50
    मै
    0.49
     öffentliche
    0.49
    絘
    0.49
    ENTES
    0.49
     conférences
    0.49
    POSITIVE LOGITS
    s
    0.54
    rip
    0.51
    eter
    0.50
    ile
    0.50
     held
    0.50
    iel
    0.47
    pa
    0.45
    ’
    0.45
     behavior
    0.45
    igan
    0.44
    Act Density 0.000%

    No Known Activations