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

    Neuronpedia

    INDEX
    Explanations

    other word or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ånd
    0.42
    ainment
    0.40
     아니
    0.40
    们
    0.40
    ीकरण
    0.39
    érence
    0.39
     किल्ला
    0.39
    全体
    0.38
    สห
    0.38
     ঘট
    0.38
    POSITIVE LOGITS
     besides
    0.62
     than
    0.53
    besides
    0.52
    Besides
    0.42
    Than
    0.42
     Than
    0.41
    another
    0.40
     niż
    0.37
     collateral
    0.37
    ELI
    0.37
    Act Density 0.010%

    No Known Activations