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

    Neuronpedia

    INDEX
    Explanations

    AMP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �n
    -0.07
     ${(
    -0.07
    넷
    -0.07
    ocoa
    -0.07
    耶
    -0.06
    aksi
    -0.06
     fj
    -0.06
     factual
    -0.06
    .IOException
    -0.06
     seeding
    -0.06
    POSITIVE LOGITS
     AMP
    0.10
     Herb
    0.07
    emple
    0.07
    _amp
    0.06
    _tickets
    0.06
     FML
    0.06
    amp
    0.06
    Modifier
    0.06
    569
    0.06
    "After
    0.06
    Act Density 0.001%

    No Known Activations