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

    Neuronpedia

    INDEX
    Explanations

    Dr. followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     próximo
    0.97
     interests
    0.93
    дви
    0.90
    諾
    0.90
    interests
    0.89
     сей
    0.88
     dotato
    0.84
     gezond
    0.83
    蹬
    0.83
     trac
    0.83
    POSITIVE LOGITS
    ಢ
    1.24
    unken
    1.24
    acula
    1.12
    ifting
    1.10
     Congo
    1.07
    ichlet
    1.03
    smanship
    1.03
    សម
    1.03
     sahab
    1.01
    innon
    1.01
    Act Density 0.130%

    No Known Activations