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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sincerity
    -0.06
    atively
    -0.06
    ''"
    -0.06
     разом
    -0.06
    Drivers
    -0.06
     leap
    -0.06
    /gtest
    -0.06
     Listening
    -0.06
     architekt
    -0.06
    -runtime
    -0.06
    POSITIVE LOGITS
    ชาว
    0.07
     masculine
    0.07
    幸
    0.06
    pository
    0.06
    Не
    0.06
    _Up
    0.06
    .updated
    0.06
    ("*
    0.06
     ；
    0.06
     orgasm
    0.06
    Act Density 0.061%

    No Known Activations