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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    싱
    -0.06
    (Field
    -0.06
     měsí
    -0.06
     강남
    -0.06
    (guild
    -0.06
     Bermuda
    -0.06
     Hits
    -0.06
     ('$
    -0.06
    mPid
    -0.06
     Suriye
    -0.06
    POSITIVE LOGITS
    speech
    0.07
     прот
    0.06
     작
    0.06
     guest
    0.06
    .tags
    0.06
    prot
    0.06
    _five
    0.06
    NSNumber
    0.06
    abytes
    0.06
     cada
    0.06
    Act Density 0.024%

    No Known Activations