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

    Neuronpedia

    INDEX
    Explanations

    technical documents and writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ।↵
    -0.08
     nursing
    -0.06
     UserId
    -0.06
     triples
    -0.06
     từ
    -0.06
     plural
    -0.06
    े।↵
    -0.06
     bedrooms
    -0.06
     яких
    -0.06
    _DAT
    -0.06
    POSITIVE LOGITS
     composer
    0.07
     Joshua
    0.06
    Benchmark
    0.06
    prov
    0.06
    680
    0.06
    oined
    0.06
    .travel
    0.06
    대의
    0.06
    efs
    0.06
    918
    0.06
    Act Density 0.000%

    No Known Activations