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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cottage
    -0.07
    .brand
    -0.07
    .en
    -0.07
    逃
    -0.07
    >To
    -0.07
    _prog
    -0.06
    ului
    -0.06
    getManager
    -0.06
     driver
    -0.06
     navigationController
    -0.06
    POSITIVE LOGITS
    -images
    0.07
    原
    0.06
    _HP
    0.06
    (MAX
    0.06
    -income
    0.06
     manos
    0.06
    restore
    0.06
    million
    0.06
     Hassan
    0.06
     bundled
    0.06
    Act Density 0.001%

    No Known Activations