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

    Neuronpedia

    INDEX
    Explanations

    numerical data and business listings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GameOver
    -0.06
    Vals
    -0.06
     convex
    -0.06
    	z
    -0.06
    Doctor
    -0.06
    Interrupt
    -0.06
     =================================================================
    -0.06
    ampoline
    -0.06
    implified
    -0.06
     importante
    -0.06
    POSITIVE LOGITS
    orse
    0.07
    .pred
    0.07
    Super
    0.06
     disgusted
    0.06
    /header
    0.06
    ヾ
    0.06
    UILD
    0.06
    rive
    0.06
    ldkf
    0.06
     rant
    0.06
    Act Density 0.009%

    No Known Activations