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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☠
    0.44
     ничего
    0.44
    も
    0.42
     кафед
    0.41
    Entire
    0.41
    ﻠ
    0.39
     څخه
    0.38
    Inicio
    0.38
     вто
    0.38
    Located
    0.38
    POSITIVE LOGITS
     terms
    1.48
     relation
    1.34
     conjunction
    1.27
     accordance
    1.13
     regards
    1.12
     lieu
    1.10
     comparison
    1.07
     contrast
    1.06
     addition
    1.05
     essence
    1.05
    Act Density 0.346%

    No Known Activations