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

    Neuronpedia

    INDEX
    Explanations

    och

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frontier
    -0.06
    yor
    -0.06
    styled
    -0.06
    greso
    -0.06
     Trotsky
    -0.06
     olup
    -0.06
     براى
    -0.06
    _minus
    -0.06
    -cycle
    -0.06
    เดอร
    -0.06
    POSITIVE LOGITS
    '),
↵
    0.07
     flights
    0.07
    uds
    0.07
     شركة
    0.07
    _SCENE
    0.06
     Websites
    0.06
    _music
    0.06
    MQ
    0.06
    Protected
    0.06
    )))
↵
    0.06
    Act Density 0.001%

    No Known Activations