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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    град
    0.82
    ruvic
    0.78
    ={`
    0.76
    তিন
    0.76
    Choice
    0.75
     ही
    0.75
    khov
    0.74
    ουσ
    0.73
    ColorF
    0.73
    Вели
    0.73
    POSITIVE LOGITS
     miejscu
    0.65
     declaraciones
    0.64
     koos
    0.63
     VIP
    0.63
     OS
    0.62
     Kill
    0.61
    ப்பட்டுள்ளன
    0.61
    त्याने
    0.61
     시절
    0.60
     вроде
    0.60
    Act Density 0.250%

    No Known Activations