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

    Neuronpedia

    INDEX
    Explanations

    follows "therefore"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heuristics
    0.49
     visualization
    0.44
    Yu
    0.44
     AUTHORS
    0.44
     heuristic
    0.44
     tarixi
    0.44
    CELL
    0.43
     होईल
    0.43
     및
    0.43
     transcript
    0.42
    POSITIVE LOGITS
    ^*\
    0.44
     powodu
    0.39
     Sena
    0.39
    ೆಯೇ
    0.38
    borderRadius
    0.38
    etil
    0.38
     Keny
    0.38
    angana
    0.38
     Sut
    0.37
    кона
    0.37
    Act Density 0.000%

    No Known Activations