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

    Neuronpedia

    INDEX
    Explanations

    theorem and threshold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    事例
    0.46
     desafio
    0.42
    務
    0.40
     reminder
    0.38
    ನ್
    0.37
    achricht
    0.36
    ay
    0.36
    art
    0.36
    提醒
    0.36
    ície
    0.36
    POSITIVE LOGITS
     thrives
    0.43
     thrive
    0.42
    ˄
    0.39
     causality
    0.39
     intelligent
    0.38
     Astoria
    0.38
     Homeland
    0.37
    liver
    0.37
    ()[
    0.37
    ophorus
    0.37
    Act Density 0.000%

    No Known Activations