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

    Neuronpedia

    INDEX
    Explanations

    carry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стояния
    0.48
     पारदर्शिता
    0.42
     perímetro
    0.41
    दाय
    0.40
    իմ
    0.40
    Só
    0.40
     movimientos
    0.39
     herkes
    0.39
    ListData
    0.39
    ListArr
    0.39
    POSITIVE LOGITS
    five
    0.41
     Creative
    0.40
     General
    0.40
     Figs
    0.39
     IEC
    0.39
    agi
    0.39
    pm
    0.38
    mml
    0.38
    ational
    0.37
     academic
    0.37
    Act Density 0.001%

    No Known Activations