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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حب
    -0.07
     Bedrooms
    -0.07
    insk
    -0.07
    부분
    -0.07
     seçim
    -0.07
    onu
    -0.07
     Armor
    -0.07
     спортив
    -0.07
    orgot
    -0.06
    onen
    -0.06
    POSITIVE LOGITS
     воздейств
    0.06
     воз
    0.06
    씩
    0.06
     Podle
    0.06
     enclave
    0.05
     прос
    0.05
     tent
    0.05
    ISODE
    0.05
    .setCode
    0.05
     sle
    0.05
    Act Density 0.157%

    No Known Activations