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

    Neuronpedia

    INDEX
    Explanations

    event bubbling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    律宾
    -0.07
    -brand
    -0.07
    );
↵
    -0.07
    -roll
    -0.06
     educate
    -0.06
    .shuffle
    -0.06
    ()})↵
    -0.06
     began
    -0.06
     編
    -0.06
    》
    -0.06
    POSITIVE LOGITS
     collo
    0.07
    至
    0.06
    esthes
    0.06
    thought
    0.06
    Unit
    0.06
    .DB
    0.06
     murky
    0.06
    อนท
    0.06
    Ù
    0.06
     Tao
    0.06
    Act Density 0.004%

    No Known Activations