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

    Neuronpedia

    INDEX
    Explanations

    kill off, taken by, units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ু
    1.08
    و
    1.05
    يه
    1.00
     தேதி
    0.98
     kræ
    0.95
    ુ
    0.94
    だけに
    0.94
    ন্ড
    0.93
    빵
    0.92
     урок
    0.92
    POSITIVE LOGITS
    es
    1.25
    גים
    1.19
    amycin
    1.17
    esy
    1.11
     randomized
    1.06
    vez
    1.05
    মুসল
    1.04
    ípio
    1.02
    ἢ
    1.01
     benzer
    1.00
    Act Density 0.000%

    No Known Activations