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

    Neuronpedia

    INDEX
    Explanations

    immun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     festive
    -0.08
    城
    -0.07
    _sched
    -0.07
     IRQ
    -0.07
    主业
    -0.07
    Nx
    -0.07
    两边
    -0.07
    NZ
    -0.07
     INSTALL
    -0.06
     inet
    -0.06
    POSITIVE LOGITS
     enlight
    0.07
    [char
    0.07
     cheer
    0.07
    _book
    0.06
     Rever
    0.06
    <IM
    0.06
     Heat
    0.06
    _LIGHT
    0.06
    _MONTH
    0.06
     thinly
    0.06
    Act Density 0.008%

    No Known Activations