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

    Neuronpedia

    INDEX
    Explanations

    Sentence start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三三三三
    -0.07
    503
    -0.06
     😉↵↵
    -0.06
     dus
    -0.06
    -makers
    -0.06
     Про
    -0.06
     potřeba
    -0.06
    (gc
    -0.06
    /ext
    -0.06
     아래
    -0.06
    POSITIVE LOGITS
     robbed
    0.06
    _kw
    0.06
    니아
    0.06
    Jeff
    0.06
     compulsory
    0.06
    Bo
    0.06
     segmentation
    0.06
     ladder
    0.06
    utomation
    0.06
    ोन
    0.06
    Act Density 0.001%

    No Known Activations