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

    Neuronpedia

    INDEX
    Explanations

    items and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অথবা
    0.42
     supremacy
    0.42
     optimality
    0.41
     détermination
    0.40
     Algorithms
    0.40
     malpractice
    0.40
     Entscheidung
    0.40
     firstNumber
    0.40
     pathogenesis
    0.39
     thisStudent
    0.39
    POSITIVE LOGITS
     a
    0.52
     plenty
    0.47
     ample
    0.46
     telefono
    0.44
    utilities
    0.44
    an
    0.43
     toilets
    0.42
     an
    0.41
    トイレ
    0.40
    A
    0.40
    Act Density 0.056%

    No Known Activations