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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الية
    -0.06
    apg
    -0.06
    mongo
    -0.06
    -db
    -0.06
     wang
    -0.06
     pou
    -0.06
    atives
    -0.06
     file
    -0.06
    -api
    -0.06
    .tags
    -0.06
    POSITIVE LOGITS
     (::
    0.07
    :bold
    0.07
     fodder
    0.07
    anyl
    0.07
    .Bar
    0.07
    lesen
    0.07
    шиб
    0.07
     Reputation
    0.06
    ясь
    0.06
    pbs
    0.06
    Act Density 0.037%

    No Known Activations