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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     These
    -0.09
     these
    -0.08
    These
    -0.08
    ประกาศ
    -0.07
     they
    -0.07
    ots
    -0.07
     são
    -0.07
    iations
    -0.07
     такими
    -0.07
     those
    -0.06
    POSITIVE LOGITS
    を使
    0.07
     qemu
    0.06
     vô
    0.06
     kitty
    0.06
    ]+
    0.06
    láv
    0.06
     галуз
    0.06
     prey
    0.06
    roe
    0.06
     lenders
    0.06
    Act Density 0.313%

    No Known Activations