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

    Neuronpedia

    INDEX
    Explanations

    Saying goodbye

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     although
    -0.10
    >{@
    -0.09
     éventuellement
    -0.08
     Wikipedia
    -0.08
     FIXME
    -0.08
    stitution
    -0.08
    unused
    -0.08
    ้อน
    -0.08
     transpose
    -0.08
    stit
    -0.08
    POSITIVE LOGITS
     �
    0.13
     �
    0.11
    ✨
    0.11
     expertly
    0.11
     showcased
    0.11
     unparalleled
    0.11
     �
    0.11
    Dubai
    0.10
    ️⃣
    0.10
    ‼
    0.10
    Act Density 0.490%

    No Known Activations