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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travelers
    -0.07
     wp
    -0.07
     preds
    -0.07
    568
    -0.07
     dac
    -0.07
     hoa
    -0.07
    /etc
    -0.06
    /Edit
    -0.06
    --;↵↵
    -0.06
    _CART
    -0.06
    POSITIVE LOGITS
     aim
    0.07
     onwards
    0.07
     너무
    0.06
     '",
    0.06
     rejuven
    0.06
     fib
    0.06
     And
    0.06
    /'+
    0.06
    ."',
    0.06
    /'.
    0.06
    Act Density 0.152%

    No Known Activations