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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ţii
    0.31
     voldo
    0.31
     Übersicht
    0.31
     destinés
    0.30
     signify
    0.30
     issus
    0.30
    براير
    0.29
     systèmes
    0.29
     existem
    0.29
     opérations
    0.29
    POSITIVE LOGITS
    but
    0.41
    and
    0.40
    。
    0.38
    for
    0.37
     but
    0.36
    4
    0.35
    6
    0.35
    AND
    0.34
    to
    0.33
     than
    0.33
    Act Density 0.052%

    No Known Activations