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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erfolgre
    -0.06
    dots
    -0.06
    ?>>
    -0.06
     bozuk
    -0.06
    .safe
    -0.06
    ụy
    -0.06
    stagram
    -0.06
    ungeons
    -0.06
     trường
    -0.06
    HOME
    -0.06
    POSITIVE LOGITS
     وسط
    0.07
     Michigan
    0.07
     emission
    0.06
    Six
    0.06
     Zoe
    0.06
    oli
    0.06
     أم
    0.06
    ι
    0.06
     ""))↵
    0.06
    -transition
    0.06
    Act Density 0.011%

    No Known Activations