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

    Neuronpedia

    INDEX
    Explanations

    label followed by colon and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asunto
    0.44
     Invite
    0.39
    ﻳ
    0.39
     endroits
    0.38
     Required
    0.38
     assuntos
    0.38
     Depend
    0.37
     prompt
    0.37
     Become
    0.37
     Places
    0.36
    POSITIVE LOGITS
     удобно
    0.47
    ów
    0.43
     había
    0.40
    渑
    0.40
    $.}
    0.40
    דם
    0.40
    ῆς
    0.38
    -}\
    0.38
    ार्ड
    0.38
    ël
    0.38
    Act Density 0.004%

    No Known Activations