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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memories
    -0.08
     albums
    -0.08
     Developers
    -0.07
     commissioners
    -0.07
     Alumni
    -0.07
    ився
    -0.07
     XIV
    -0.07
    -css
    -0.06
    ={}
    -0.06
     level
    -0.06
    POSITIVE LOGITS
     wonder
    0.06
    ouched
    0.06
    __;↵
    0.06
     �
    0.06
     nimi
    0.06
     Manip
    0.06
     έκ
    0.06
    (Controller
    0.06
     groundwater
    0.06
    lediği
    0.06
    Act Density 0.039%

    No Known Activations