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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .blit
    -0.07
     ortak
    -0.07
    .Touch
    -0.07
    álních
    -0.07
    ozem
    -0.06
    ();
    -0.06
    apyrus
    -0.06
    题
    -0.06
     WhatsApp
    -0.06
    jualan
    -0.06
    POSITIVE LOGITS
     Schumer
    0.06
     presenter
    0.06
    485
    0.06
    ":{↵
    0.06
    [column
    0.06
    [v
    0.06
    Nine
    0.06
    ]
↵
↵
    0.06
    >s
    0.06
    0.06
    Act Density 0.097%

    No Known Activations