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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kali
    -0.06
    mdb
    -0.06
    trak
    -0.06
     땅
    -0.06
    PIO
    -0.06
     역사
    -0.06
     فرو
    -0.06
    країн
    -0.06
    言って
    -0.06
    .bot
    -0.06
    POSITIVE LOGITS
    Marcus
    0.07
     Panthers
    0.07
     Naples
    0.06
     scientific
    0.06
     analytical
    0.06
    License
    0.06
    ugging
    0.06
     %"
    0.06
     Hutchinson
    0.06
     muzzle
    0.06
    Act Density 0.062%

    No Known Activations