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

    Neuronpedia

    INDEX
    Explanations

    infrared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setup
    -0.07
    也正是
    -0.07
     cuanto
    -0.06
    Micro
    -0.06
    udios
    -0.06
    �
    -0.06
    .types
    -0.06
    _WIDTH
    -0.06
    迨
    -0.06
    苔
    -0.06
    POSITIVE LOGITS
     tour
    0.07
    嬰
    0.07
    scious
    0.07
     literals
    0.07
    嶓
    0.07
    ivist
    0.07
     adulti
    0.06
     eg
    0.06
     Hulk
    0.06
    aper
    0.06
    Act Density 0.002%

    No Known Activations