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

    Neuronpedia

    INDEX
    Explanations

    Linear Elastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $\{(
    0.45
     ხელ
    0.44
    ಥ
    0.44
    ்ட
    0.43
     редакти
    0.43
    eneral
    0.43
    ue
    0.42
     سلس
    0.42
     eup
    0.42
    ٴ
    0.42
    POSITIVE LOGITS
    ENV
    0.44
     pledge
    0.39
     écologique
    0.39
     ENV
    0.39
    ANK
    0.38
    襁
    0.38
     pageant
    0.38
    env
    0.38
     JavaScript
    0.38
     academies
    0.38
    Act Density 0.000%

    No Known Activations