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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ebek
    -0.08
     ---------
    -0.07
     le
    -0.07
     partnered
    -0.07
    please
    -0.07
     seule
    -0.07
     election
    -0.06
    onClick
    -0.06
    Company
    -0.06
    Confirm
    -0.06
    POSITIVE LOGITS
     IRA
    0.06
    (ierr
    0.06
    !="
    0.06
     rer
    0.06
    ution
    0.06
    ีท
    0.06
    .youtube
    0.06
    رد
    0.06
     اه
    0.06
    �
    0.06
    Act Density 0.027%

    No Known Activations