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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wyn
    -0.07
    노
    -0.07
     navig
    -0.07
     peut
    -0.06
     paraph
    -0.06
     enthusi
    -0.06
     soph
    -0.06
     disemb
    -0.06
     moh
    -0.06
     Jur
    -0.06
    POSITIVE LOGITS
    avings
    0.07
    ="-
    0.06
     RESOURCE
    0.06
    .delete
    0.06
    _modify
    0.06
     свої
    0.06
     dads
    0.06
    -www
    0.06
    urning
    0.06
    255
    0.06
    Act Density 0.000%

    No Known Activations