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

    Neuronpedia

    INDEX
    Explanations

    LEFT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .verify
    -0.07
    _assign
    -0.07
    :",
    -0.07
    -Americans
    -0.07
    .check
    -0.07
    购
    -0.07
    .Search
    -0.07
    cete
    -0.07
     herr
    -0.07
     NoSuch
    -0.06
    POSITIVE LOGITS
    ẳn
    0.07
    тя
    0.06
     Specifically
    0.06
     والتي
    0.06
     Extremely
    0.06
    几个
    0.06
     zaměstn
    0.06
     hardship
    0.06
    inceton
    0.06
    tvrt
    0.05
    Act Density 0.001%

    No Known Activations