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

    Neuronpedia

    INDEX
    Explanations

    code and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _"
    -0.06
    (~
    -0.06
    .NoError
    -0.06
     Athen
    -0.06
    喊
    -0.06
    _zoom
    -0.06
    .Stream
    -0.06
     Democratic
    -0.06
    PRETTY
    -0.06
     teachings
    -0.06
    POSITIVE LOGITS
     segunda
    0.07
     fate
    0.07
     후보
    0.07
    _PROFILE
    0.07
    flower
    0.06
    ngör
    0.06
    _references
    0.06
     prime
    0.06
     turnovers
    0.06
    acebook
    0.06
    Act Density 0.013%

    No Known Activations