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

    Neuronpedia

    INDEX
    Explanations

    .ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Space
    -0.08
     Grocery
    -0.08
    Vertex
    -0.07
    eten
    -0.07
    に基
    -0.07
     Generated
    -0.07
    _exists
    -0.07
    上看
    -0.07
    punk
    -0.07
     oasis
    -0.07
    POSITIVE LOGITS
    利物浦
    0.07
    .Div
    0.06
    .um
    0.06
    迎来
    0.06
    连
    0.06
     Links
    0.06
     LIB
    0.06
    용
    0.06
     �
    0.06
     shares
    0.06
    Act Density 0.001%

    No Known Activations