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

    Neuronpedia

    INDEX
    Explanations

    Legal references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    simp
    -0.07
    Sup
    -0.07
     distancing
    -0.07
    Dr
    -0.06
    edar
    -0.06
    —the
    -0.06
     Cheng
    -0.06
     NE
    -0.06
     EMP
    -0.06
    Wall
    -0.06
    POSITIVE LOGITS
     후보
    0.07
     αυ
    0.07
    .bid
    0.07
    .AddModelError
    0.06
    .calculate
    0.06
    %timeout
    0.06
    .connector
    0.06
    81
    0.06
    ід
    0.06
    :::::::::::::
    0.06
    Act Density 0.004%

    No Known Activations