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

    Neuronpedia

    INDEX
    Explanations

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lies
    -0.07
    ीद
    -0.07
    ẵ
    -0.06
     getPage
    -0.06
    -inst
    -0.06
    Năm
    -0.06
     nghị
    -0.06
    Pref
    -0.06
    _backend
    -0.06
     Matthew
    -0.06
    POSITIVE LOGITS
     εφαρ
    0.07
    ۱۳
    0.07
     配
    0.07
     giải
    0.06
     "---
    0.06
    LEGRO
    0.06
     zusammen
    0.06
     �
    0.06
     常
    0.06
     розк
    0.06
    Act Density 0.022%

    No Known Activations