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

    Neuronpedia

    INDEX
    Explanations

    location services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )."
    0.60
     can
    0.58
     splitter
    0.58
     billi
    0.57
     peque
    0.56
     miejscu
    0.56
     harem
    0.56
    )
    0.56
     día
    0.55
     hoặc
    0.55
    POSITIVE LOGITS
    Фор
    0.52
    MO
    0.52
    Ч
    0.51
    cek
    0.50
    getCurrent
    0.50
    pbs
    0.50
    Current
    0.49
    Ал
    0.48
    ొ
    0.48
    Н
    0.48
    Act Density 0.001%

    No Known Activations