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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cy
    -0.07
     вог
    -0.06
    *y
    -0.06
    火
    -0.06
     nargs
    -0.06
    _closed
    -0.06
     cyk
    -0.06
     tent
    -0.06
    —with
    -0.06
    xlim
    -0.06
    POSITIVE LOGITS
    ija
    0.07
    .FALSE
    0.07
     socket
    0.06
    已经
    0.06
    ст
    0.06
    olean
    0.06
    lok
    0.06
     warranty
    0.06
    aset
    0.06
     Slav
    0.06
    Act Density 0.000%

    No Known Activations