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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कहन
    -0.06
    .samples
    -0.06
     partnered
    -0.06
     gentlemen
    -0.06
    уп
    -0.06
    狗
    -0.06
    %),
    -0.06
    _movement
    -0.06
    ispiel
    -0.06
     Darren
    -0.06
    POSITIVE LOGITS
     Irvine
    0.07
    HELL
    0.07
    caff
    0.06
     thumbs
    0.06
     ordinances
    0.06
    osci
    0.06
     ctor
    0.06
    IDO
    0.06
     Th
    0.06
    -mediated
    0.06
    Act Density 0.020%

    No Known Activations