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

    Neuronpedia

    INDEX
    Explanations

    audiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Купить
    -0.08
    .Wh
    -0.07
     professors
    -0.07
     אחרונים
    -0.07
     señor
    -0.07
     כש
    -0.07
     KV
    -0.06
       ↵↵
    -0.06
    손
    -0.06
    אשר
    -0.06
    POSITIVE LOGITS
    放映
    0.08
     "()
    0.08
     актив
    0.07
    interested
    0.07
    oproject
    0.07
    ethyst
    0.07
     routed
    0.06
     estamos
    0.06
    DBC
    0.06
    elerik
    0.06
    Act Density 0.002%

    No Known Activations