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

    Neuronpedia

    INDEX
    Explanations

    problem, solution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spider
    -0.09
     bitters
    -0.07
     青
    -0.07
     તરીકે
    -0.07
    fiber
    -0.07
    -0.07
    -0.07
    @yahoo
    -0.07
    acher
    -0.07
     челов
    -0.07
    POSITIVE LOGITS
     बल्कि
    0.17
     بلکہ
    0.16
     אלא
    0.16
     بلکه
    0.14
     sondern
    0.14
    ，而且
    0.14
     तत्काल
    0.12
     وإنما
    0.11
     sino
    0.11
    뿐
    0.10
    Act Density 0.130%
    No Known Activations