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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nech
    -0.07
     suspend
    -0.07
    هن
    -0.07
    onaut
    -0.06
     Alt
    -0.06
    Alt
    -0.06
     CK
    -0.06
    (updated
    -0.06
    _COMPONENT
    -0.06
     monitor
    -0.06
    POSITIVE LOGITS
     certify
    0.06
     Hom
    0.06
     friendships
    0.06
     처리
    0.06
    腰
    0.06
     promoters
    0.06
    oard
    0.06
    NG
    0.06
     OPP
    0.05
     fleet
    0.05
    Act Density 0.016%

    No Known Activations