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

    Neuronpedia

    INDEX
    Explanations

    sever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rostlin
    -0.07
     domácí
    -0.06
    鸟
    -0.06
    /logout
    -0.06
    CAPE
    -0.06
     oldukları
    -0.06
     DECL
    -0.06
    地域
    -0.06
    _daily
    -0.06
    rowth
    -0.06
    POSITIVE LOGITS
     sever
    0.15
     severed
    0.14
     Sever
    0.14
     Sq
    0.07
     terminates
    0.07
    ver
    0.07
     Offer
    0.07
    VERY
    0.07
    _GAIN
    0.07
    vw
    0.07
    Act Density 0.001%

    No Known Activations