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

    Neuronpedia

    INDEX
    Explanations

    choices or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.68
    এবং
    0.57
     observed
    0.48
     encouraged
    0.45
     extraordinaire
    0.45
    και
    0.43
    りと
    0.42
     targets
    0.41
    ায়ণের
    0.41
    syair
    0.41
    POSITIVE LOGITS
     или
    3.97
     அல்லது
    3.75
    或
    3.73
     veya
    3.70
    หรือ
    3.66
     ಅಥವಾ
    3.63
     hoặc
    3.56
     किंवा
    3.55
     અથવા
    3.55
     or
    3.44
    Act Density 1.033%

    No Known Activations