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

    Neuronpedia

    INDEX
    Explanations

    introducing new topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     where
    -1.66
     in
    -1.54
     at
    -1.54
     after
    -1.54
     on
    -1.53
     still
    -1.38
     by
    -1.34
     L
    -1.34
     through
    -1.34
     Кубка
    -1.33
    POSITIVE LOGITS
    感じで
    1.59
     regarde
    1.56
    ほら
    1.55
     péro
    1.45
     dites
    1.41
     rocha
    1.39
    感じが
    1.36
     principali
    1.34
     LIRE
    1.34
     concr
    1.33
    Act Density 0.560%

    No Known Activations