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

    Neuronpedia

    INDEX
    Explanations

    name in, name evokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bernama
    0.82
    ם
    0.64
     them
    0.61
    므로
    0.61
     lilac
    0.61
    으며
    0.59
    ных
    0.59
    aniyam
    0.58
     named
    0.58
     beanie
    0.57
    POSITIVE LOGITS
    s
    0.92
    0
    0.79
    K
    0.73
    ر
    0.68
    LL
    0.57
    }")
    0.57
    P
    0.56
    },
    0.55
    }*/
    0.55
     Rankings
    0.55
    Act Density 0.015%

    No Known Activations