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

    Neuronpedia

    INDEX
    Explanations

    dog bob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     felse
    -0.07
     preempt
    -0.07
    完成
    -0.07
     strtol
    -0.07
     zdroj
    -0.07
    Volume
    -0.07
     empt
    -0.07
     fundra
    -0.06
    傳
    -0.06
    ‌شد
    -0.06
    POSITIVE LOGITS
     Pirate
    0.08
    μπο
    0.08
     各
    0.07
    AT
    0.07
     Boy
    0.07
     rat
    0.06
     Hod
    0.06
    Client
    0.06
    باب
    0.06
     Cow
    0.06
    Act Density 0.024%

    No Known Activations