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

    Neuronpedia

    INDEX
    Explanations

    based on or unique maximum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MAKING
    0.55
     Antwerp
    0.49
    <0x89>
    0.48
    㡺
    0.46
     Making
    0.45
     দেবতাদের
    0.45
     तिजारत
    0.45
    ্যা
    0.45
     安
    0.44
     』
    0.44
    POSITIVE LOGITS
    ින්
    0.47
    Pier
    0.45
    偲
    0.43
     sapp
    0.43
     cab
    0.42
    ध
    0.42
    ﻧ
    0.41
    کل
    0.41
     jasno
    0.40
    nię
    0.40
    Act Density 0.000%

    No Known Activations