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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dne
    -0.07
    -sama
    -0.07
    ΕΙΣ
    -0.06
     died
    -0.06
     Weak
    -0.06
    PFN
    -0.06
    君
    -0.06
     Vendor
    -0.06
    threshold
    -0.06
     Builds
    -0.06
    POSITIVE LOGITS
    ßen
    0.07
    sstream
    0.06
    	esc
    0.06
    Instructions
    0.06
     overseeing
    0.06
    　ｌ
    0.06
     ridiculously
    0.06
    _FUNCTION
    0.06
    Textbox
    0.06
     podporu
    0.06
    Act Density 0.013%

    No Known Activations