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

    Neuronpedia

    INDEX
    Explanations

    Dialogue/Narrative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Serve
    -0.06
    καν
    -0.06
    Toyota
    -0.06
    다가
    -0.06
    _Order
    -0.06
     "//
    -0.06
     quad
    -0.06
    ERSION
    -0.06
     //_
    -0.06
    电视
    -0.06
    POSITIVE LOGITS
    features
    0.07
     dictates
    0.07
     혹
    0.07
    ATORY
    0.06
    τία
    0.06
    امبر
    0.06
    ']="
    0.06
    Verifier
    0.06
    acidad
    0.06
     outskirts
    0.06
    Act Density 0.143%

    No Known Activations