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

    Neuronpedia

    INDEX
    Explanations

    responsible, kills, flexibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INO
    0.89
    ్‌
    0.85
    ung
    0.82
     quién
    0.82
     incluyendo
    0.80
     бренда
    0.80
     Второй
    0.79
    rs
    0.77
    yo
    0.77
     quien
    0.77
    POSITIVE LOGITS
    护
    0.79
    Οι
    0.76
    ไร
    0.75
    護
    0.74
     clogged
    0.71
     gasket
    0.70
     precipit
    0.70
     precipitated
    0.69
     goutte
    0.69
     Akar
    0.67
    Act Density 0.000%

    No Known Activations