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

    Neuronpedia

    INDEX
    Explanations

    obviously clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused87>
    0.67
    BackgroundTask
    0.65
     sağlıklı
    0.65
     specie
    0.64
     réduite
    0.64
     procé
    0.64
     ধৈর্য
    0.63
     vork
    0.63
    Estim
    0.62
    璐
    0.62
    POSITIVE LOGITS
     obvious
    3.95
     obviously
    2.97
     evident
    2.75
     évident
    2.71
     evidente
    2.65
    obviously
    2.62
     оче
    2.56
     Obviously
    2.53
    Obviously
    2.49
    明显的
    2.48
    Act Density 0.378%

    No Known Activations