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

    Neuronpedia

    INDEX
    Explanations

    manuscript references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LINE
    -0.06
     kort
    -0.06
    /image
    -0.06
    …and
    -0.06
     Fires
    -0.06
    .Static
    -0.06
    .bus
    -0.06
     Convenient
    -0.06
     heads
    -0.06
     aVar
    -0.06
    POSITIVE LOGITS
    علی
    0.06
    ippets
    0.06
    gamber
    0.06
     premature
    0.06
    UU
    0.06
     подраз
    0.06
    elaide
    0.06
    .every
    0.06
    ‌انبار
    0.06
     pci
    0.06
    Act Density 0.006%

    No Known Activations