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

    Neuronpedia

    INDEX
    Explanations

    mobile, models, microscopic, tiny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     candy
    0.46
     कैंडी
    0.41
     subway
    0.40
     Triton
    0.40
    candy
    0.39
     km
    0.39
     gar
    0.38
     underwriting
    0.38
     visual
    0.37
     underground
    0.37
    POSITIVE LOGITS
    ónde
    0.42
     ಅಮ
    0.41
    藻
    0.39
    ﺂ
    0.38
    ộ
    0.38
    វេ
    0.37
    분을
    0.37
    邮箱
    0.36
     alcançar
    0.36
    ScrollPane
    0.35
    Act Density 0.000%

    No Known Activations