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

    Neuronpedia

    INDEX
    Explanations

    ac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    407
    -0.08
    .md
    -0.08
    _encrypt
    -0.07
    	assertTrue
    -0.07
    bmp
    -0.07
     Installing
    -0.06
    	win
    -0.06
     ein
    -0.06
     зміни
    -0.06
     Dương
    -0.06
    POSITIVE LOGITS
    нак
    0.06
    قف
    0.06
    (hex
    0.06
    cean
    0.06
    GetProcAddress
    0.06
     acupuncture
    0.06
     Shar
    0.06
     tuned
    0.06
    に向
    0.06
    _light
    0.06
    Act Density 0.004%

    No Known Activations