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

    Neuronpedia

    INDEX
    Explanations

    exactly what/how/the/to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    2.48
     covalently
    2.35
     عادی
    2.32
     kiire
    2.21
     truly
    2.11
     écart
    2.07
     êtres
    2.04
     drooping
    2.00
     рӯ
    1.97
     Daar
    1.96
    POSITIVE LOGITS
    दीश
    2.35
    מו
    2.20
    selves
    2.14
    ни
    2.14
    cles
    2.13
    vspace
    2.10
     dateTime
    2.08
    ن
    2.04
    oost
    2.03
     conjunt
    2.01
    Act Density 0.076%

    No Known Activations