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

    Neuronpedia

    INDEX
    Explanations

    consider size or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ബ്ര
    0.43
     জাহাঙ্গীর
    0.41
    質問
    0.38
     lingered
    0.38
     maxLength
    0.37
     endeavoured
    0.37
     shipped
    0.37
     venom
    0.37
     prona
    0.37
     plante
    0.36
    POSITIVE LOGITS
    Intrinsic
    0.45
    War
    0.43
     War
    0.42
    Be
    0.41
    Session
    0.40
    wash
    0.40
    Economics
    0.39
    intrinsic
    0.39
    Ar
    0.38
    Crypt
    0.38
    Act Density 0.002%

    No Known Activations