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

    Neuronpedia

    INDEX
    Explanations

    direct or closest alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plates
    0.42
     components
    0.42
     étape
    0.41
     solutions
    0.40
     spark
    0.40
     sparks
    0.40
    ]:
    0.40
     blocks
    0.39
     هناك
    0.38
     steps
    0.38
    POSITIVE LOGITS
    ре
    0.43
    hauled
    0.42
    𝒆
    0.41
    ዴ
    0.41
    ну
    0.40
    മീ
    0.39
    𝗻
    0.39
    нуу
    0.39
    mover
    0.38
    relationship
    0.38
    Act Density 0.000%

    No Known Activations