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

    Neuronpedia

    INDEX
    Explanations

    Further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onest
    -0.07
    =is
    -0.07
    osaic
    -0.07
    ecause
    -0.06
    abcdefghijklmnopqrstuvwxyz
    -0.06
    lord
    -0.06
    娜
    -0.06
    -Time
    -0.06
     Because
    -0.06
     owns
    -0.06
    POSITIVE LOGITS
     further
    0.23
    Further
    0.18
     Further
    0.17
     farther
    0.12
    urther
    0.10
    进一步
    0.08
    Far
    0.07
     counselling
    0.07
     даль
    0.07
     dál
    0.07
    Act Density 0.020%

    No Known Activations