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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quotid
    -0.07
    OVE
    -0.07
    .med
    -0.07
    alat
    -0.06
     sharper
    -0.06
    ाप
    -0.06
    Messages
    -0.06
    /day
    -0.06
    utenant
    -0.06
    ヴ
    -0.06
    POSITIVE LOGITS
     grpc
    0.07
    argout
    0.07
    983
    0.07
     confidently
    0.06
    -post
    0.06
    989
    0.06
     Accountability
    0.06
    ube
    0.06
    mvc
    0.06
    _hierarchy
    0.06
    Act Density 0.004%

    No Known Activations