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

    Neuronpedia

    INDEX
    Explanations

    character builder scaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    成為
    0.47
    ľ
    0.46
    ر
    0.45
    loc
    0.45
    無
    0.45
    falling
    0.44
    atives
    0.44
    ジェル
    0.44
    repetitions
    0.43
    ન
    0.43
    POSITIVE LOGITS
     eukary
    0.48
     TOWN
    0.44
     wagg
    0.44
     Qian
    0.44
     构建
    0.43
     buildFor
    0.43
     riego
    0.43
     Town
    0.42
     молока
    0.42
    TrackAngle
    0.42
    Act Density 0.001%

    No Known Activations