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

    Neuronpedia

    INDEX
    Explanations

    gradle dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    androidTest
    0.44
     Ne
    0.38
    ុំ
    0.38
    Pan
    0.38
    contribution
    0.37
    Ne
    0.37
    ultz
    0.37
    אַר
    0.37
    ार्म
    0.36
     Fos
    0.36
    POSITIVE LOGITS
     NGF
    0.43
     (\<
    0.40
    ాని
    0.40
    Callable
    0.40
     เพียง
    0.39
     Only
    0.38
    LayoutStyle
    0.38
     Lombok
    0.38
    voren
    0.38
     ench
    0.38
    Act Density 0.001%

    No Known Activations