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

    Neuronpedia

    INDEX
    Explanations

    names and skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಂಟ
    0.43
     ಮಕ್ಕ
    0.42
     innehåller
    0.41
     ಸಾಧ್ಯ
    0.39
    陨
    0.38
    "})
    0.38
    🐗
    0.38
    බැ
    0.38
     enthalten
    0.38
    Verse
    0.37
    POSITIVE LOGITS
    iliations
    0.42
     Nadine
    0.41
    Amy
    0.40
     Waco
    0.40
    ጵ
    0.40
     Amy
    0.40
     Houston
    0.39
     Wendy
    0.39
    or
    0.39
     Kathryn
    0.38
    Act Density 0.004%

    No Known Activations