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

    Neuronpedia

    INDEX
    Explanations

    definitions and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    銠
    0.40
     Fransiya
    0.38
    ठभे
    0.38
    (&:
    0.38
     váy
    0.37
    0.37
    𝔞
    0.37
     pâte
    0.36
    脿
    0.36
    ához
    0.36
    POSITIVE LOGITS
    t
    0.43
     Sever
    0.42
     non
    0.41
     Hu
    0.40
    PO
    0.39
     cancellation
    0.39
    AI
    0.38
     If
    0.38
     may
    0.38
    Min
    0.37
    Act Density 0.000%

    No Known Activations