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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _compile
    -0.07
    _corners
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
    Refs
    -0.06
     Ін
    -0.06
    desc
    -0.06
    _linux
    -0.06
    окон
    -0.06
    _xx
    -0.06
    Fac
    -0.06
    POSITIVE LOGITS
     음
    0.08
     assass
    0.07
    _SD
    0.07
     SM
    0.06
    �
    0.06
     Vz
    0.06
     Sole
    0.06
    ancial
    0.06
     stom
    0.06
    ออ
    0.06
    Act Density 0.001%

    No Known Activations