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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _targets
    -0.07
    \system
    -0.07
     bers
    -0.07
    (constants
    -0.07
    _navigation
    -0.07
    .setHorizontal
    -0.07
     Commissioners
    -0.07
    _MAPPING
    -0.07
     jub
    -0.07
    的精神
    -0.07
    POSITIVE LOGITS
     skincare
    0.07
     blanket
    0.07
     liken
    0.07
     thankful
    0.06
    防水
    0.06
     crow
    0.06
    张某
    0.06
     wipes
    0.06
    通讯员
    0.06
    相对于
    0.06
    Act Density 0.015%

    No Known Activations