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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Names
    -0.06
    .=
    -0.06
    _);↵↵
    -0.06
     McInt
    -0.06
     Tibet
    -0.06
    _rhs
    -0.06
    哪里
    -0.06
    awe
    -0.06
     意
    -0.05
     praying
    -0.05
    POSITIVE LOGITS
     "{{
    0.07
     신청
    0.07
    .BACK
    0.07
    Anyone
    0.06
    'était
    0.06
    DSP
    0.06
    Оп
    0.06
     mundane
    0.06
    expectException
    0.06
    영
    0.06
    Act Density 0.004%

    No Known Activations