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

    Neuronpedia

    INDEX
    Explanations

    kinds and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     информацией
    0.45
    𝄞
    0.45
     untersucht
    0.44
    囦
    0.44
    转型
    0.43
     besucht
    0.43
    బడు
    0.42
     давайте
    0.41
    牞
    0.41
    ľov
    0.41
    POSITIVE LOGITS
     Z
    0.51
     z
    0.48
    po
    0.46
     kinds
    0.44
    ज़
    0.44
     Y
    0.43
     types
    0.43
    is
    0.43
     subt
    0.43
     zast
    0.43
    Act Density 0.036%

    No Known Activations