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

    Neuronpedia

    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WARDED
    -0.07
     unwind
    -0.06
     follando
    -0.06
     erotico
    -0.06
     přičemž
    -0.06
    (DEFAULT
    -0.06
     armed
    -0.06
     incor
    -0.05
    LOPT
    -0.05
     wrestler
    -0.05
    POSITIVE LOGITS
    ena
    0.07
    aires
    0.06
     ва
    0.06
    وا
    0.06
     Initialise
    0.06
     Vintage
    0.06
     أش
    0.06
     awk
    0.06
    _af
    0.06
    ологіч
    0.06
    Act Density 0.000%

    No Known Activations