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

    Neuronpedia

    INDEX
    Explanations

    actions followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izing
    0.68
     serían
    0.62
    amis
    0.60
    isation
    0.57
    ising
    0.57
    ization
    0.56
    ial
    0.56
    isasi
    0.54
     ﺍﻟ
    0.54
    ality
    0.53
    POSITIVE LOGITS
    ר
    0.81
    ט
    0.74
    ד
    0.72
    ת
    0.71
    ז
    0.71
    ס
    0.70
    ле
    0.69
    Ш
    0.68
    ה
    0.62
    ש
    0.61
    Act Density 0.930%

    No Known Activations