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

    Neuronpedia

    INDEX
    Explanations

    space opera

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    인지
    0.60
    ا
    0.60
     observado
    0.60
    Ი
    0.59
    Ბ
    0.59
    کا
    0.58
    ла
    0.58
    과학
    0.57
    علم
    0.57
     alimentar
    0.57
    POSITIVE LOGITS
     by
    0.55
     второй
    0.53
     t
    0.48
     g
    0.47
    by
    0.46
     опа
    0.46
     одина
    0.45
     v
    0.44
    r
    0.44
     vi
    0.44
    Act Density 0.000%

    No Known Activations