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

    Neuronpedia

    INDEX
    Explanations

    speaker, patient, user, customer roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manten
    1.12
    ♻
    0.95
    。『
    0.93
    ‌.
    0.88
     possibilit
    0.85
    ביל
    0.83
    osiery
    0.81
     Southwest
    0.81
     Incidentally
    0.81
    ™.
    0.81
    POSITIVE LOGITS
    }\
    1.01
    들은
    1.00
    ನೇ
    0.97
     sitzt
    0.89
     βρίσκεται
    0.87
    者が
    0.84
    ων
    0.83
     показа
    0.83
    ರ್ಭ
    0.82
     Nxg
    0.81
    Act Density 0.244%

    No Known Activations