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

    Neuronpedia

    INDEX
    Explanations

    George and Thomas names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことになる
    1.03
    asibility
    0.92
    𝖽
    0.85
     tuleb
    0.84
     każdy
    0.83
    こと
    0.83
     cậu
    0.83
    roscopy
    0.83
     wówczas
    0.82
    薅
    0.82
    POSITIVE LOGITS
     EL
    0.73
     ms
    0.72
    }
    0.68
    빅
    0.66
     modern
    0.64
     H
    0.64
     IV
    0.64
    х
    0.63
     MS
    0.63
     planting
    0.63
    Act Density 0.000%

    No Known Activations