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

    Neuronpedia

    INDEX
    Explanations

    list of project dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    、
    0.54
    。
    0.52
    ると
    0.49
    ，
    0.47
    甲
    0.47
    柑
    0.47
    や
    0.46
    スト
    0.44
    下
    0.43
    Mai
    0.43
    POSITIVE LOGITS
     aureus
    0.51
     dependencies
    0.50
     psychopath
    0.50
     appraised
    0.50
     materialism
    0.50
     cujo
    0.49
     thermodynam
    0.49
     hydraul
    0.49
     columns
    0.48
    giz
    0.48
    Act Density 0.000%

    No Known Activations