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

    Neuronpedia

    INDEX
    Explanations

    alternatives and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
    ayan
    -0.08
     ([
    -0.08
    staw
    -0.07
    LICK
    -0.07
    łącz
    -0.07
    iedy
    -0.07
     �
    -0.07
     나타
    -0.07
     Ош
    -0.07
    POSITIVE LOGITS
     genuine
    0.11
     legitimate
    0.10
     respectful
    0.10
     responsibly
    0.09
     reputable
    0.09
     безопас
    0.09
     sincerely
    0.09
     safer
    0.09
    正规的
    0.09
     safely
    0.09
    Act Density 0.056%

    No Known Activations