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

    Neuronpedia

    INDEX
    Explanations

    connectors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nisu
    -0.08
    тура
    -0.08
    repid
    -0.08
    OWN
    -0.08
     niso
    -0.08
    _ENDPOINT
    -0.08
     moderate
    -0.08
     екен
    -0.08
    .DE
    -0.08
     sain
    -0.08
    POSITIVE LOGITS
     클릭
    0.08
     꽃
    0.08
    _merge
    0.07
     표시
    0.07
    ాల్స
    0.07
     내부
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    遮
    0.07
    Merge
    0.07
     merging
    0.07
    Act Density 0.006%

    No Known Activations