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

    Neuronpedia

    INDEX
    Explanations

    sale, claim, Personal, inverting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deoarece
    0.45
    Loans
    0.44
    Bin
    0.44
    Spray
    0.43
    Collapse
    0.43
     எவ்வாறு
    0.43
     protože
    0.42
    AS
    0.42
     proche
    0.42
    Loan
    0.42
    POSITIVE LOGITS
     immaculate
    0.49
     meticulous
    0.49
     careless
    0.45
     whimsical
    0.45
     fantastical
    0.45
     boasting
    0.44
     worldly
    0.44
     admiring
    0.44
     meticulously
    0.43
     monotonous
    0.43
    Act Density 0.000%

    No Known Activations