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

    Neuronpedia

    INDEX
    Explanations

    prompts and platform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sprinkles
    0.49
     Dac
    0.45
     ಖರೀ
    0.45
     scall
    0.44
     terrasse
    0.44
     dast
    0.44
    মুর
    0.44
    晗
    0.44
     минима
    0.43
     信息
    0.43
    POSITIVE LOGITS
    ↵↵
    0.54
    $\
    0.48
    (
    0.48
     टिप्पणी
    0.47
    batim
    0.47
    遡
    0.46
    candidate
    0.46
    el
    0.46
     संबोधित
    0.46
     narrative
    0.45
    Act Density 0.000%

    No Known Activations