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

    Neuronpedia

    INDEX
    Explanations

    reducing disease risk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Username
    -0.07
    entered
    -0.07
    Rec
    -0.07
    Group
    -0.06
    -group
    -0.06
    idel
    -0.06
    abler
    -0.06
    strap
    -0.06
     arrays
    -0.06
    Instagram
    -0.06
    POSITIVE LOGITS
     такое
    0.07
     topl
    0.07
     bảo
    0.06
     몽
    0.06
    .lastIndexOf
    0.06
     HOL
    0.06
    _seed
    0.06
     exercitation
    0.06
     bağ
    0.06
    …and
    0.06
    Act Density 0.037%

    No Known Activations