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

    Neuronpedia

    INDEX
    Explanations

    streams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IM
    -0.08
    argar
    -0.08
     Radi
    -0.08
     IMF
    -0.07
     Wind
    -0.07
     trusted
    -0.07
     Emergency
    -0.07
     diplomat
    -0.07
     (#
    -0.07
     seller
    -0.07
    POSITIVE LOGITS
    .Collectors
    0.09
     macam
    0.08
     modernos
    0.08
     processamento
    0.08
     boli
    0.08
     поток
    0.08
    <Post
    0.08
     tentative
    0.08
    .Please
    0.08
    িছিল
    0.08
    Act Density 0.008%

    No Known Activations