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

    Neuronpedia

    INDEX
    Explanations

    exists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .outer
    -0.06
     '"
    -0.06
     souvenir
    -0.06
     Redirect
    -0.06
    .Resume
    -0.06
    bring
    -0.06
     Bez
    -0.06
    _Header
    -0.06
    //------------------------------------------------------------------------------------------------
    -0.06
    _surf
    -0.06
    POSITIVE LOGITS
     Award
    0.07
     JACK
    0.07
     award
    0.06
    ship
    0.06
    DEL
    0.06
    ائی
    0.06
    irts
    0.06
    ны
    0.06
    del
    0.06
     hardened
    0.06
    Act Density 0.003%

    No Known Activations