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

    Neuronpedia

    INDEX
    Explanations

    multi-dimensional, multi-part, multi-factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     적
    0.75
    Arte
    0.68
     kreatif
    0.68
     Astrophys
    0.67
     ஒவ்வ
    0.66
    全体
    0.66
    राल
    0.65
     뒷
    0.65
    ავს
    0.65
    烂
    0.65
    POSITIVE LOGITS
     dimensional
    1.66
    dimensional
    1.59
    Dimensional
    1.57
     sided
    1.52
     prong
    1.47
     Dimensional
    1.44
    pronged
    1.43
     diment
    1.42
    fold
    1.38
    sided
    1.37
    Act Density 0.197%

    No Known Activations