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

    Neuronpedia

    INDEX
    Explanations

    electronics and building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    許
    -0.07
     Olsen
    -0.07
    GetY
    -0.07
    Strike
    -0.07
    atty
    -0.07
    分类
    -0.06
    кового
    -0.06
     Patty
    -0.06
     ips
    -0.06
    _rule
    -0.06
    POSITIVE LOGITS
     �
    0.07
    SharedPointer
    0.07
     ابراه
    0.06
     федераль
    0.06
     disables
    0.06
     plaisir
    0.06
     ren
    0.06
     roman
    0.06
     robin
    0.06
     ----
    0.06
    Act Density 0.322%

    No Known Activations