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

    Neuronpedia

    INDEX
    Explanations

    choosing from or what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чный
    1.04
     ativos
    0.89
     verdade
    0.89
     этому
    0.87
    t
    0.86
     учены
    0.84
    ỡng
    0.82
     خاطر
    0.79
    aneers
    0.79
     Кстати
    0.79
    POSITIVE LOGITS
    :
    0.77
     legs
    0.71
    :]
    0.68
    .],
    0.68
    ],
    0.67
    קט
    0.67
    דיה
    0.67
    غط
    0.66
    פות
    0.65
     intimidated
    0.65
    Act Density 0.000%

    No Known Activations