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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ગામ
    -0.08
     empezó
    -0.08
     comenzó
    -0.08
    	try
    -0.08
    .Marshal
    -0.07
    iał
    -0.07
    ïs
    -0.07
     communes
    -0.07
     mairie
    -0.07
    HAS
    -0.07
    POSITIVE LOGITS
     doubled
    0.09
     multiple
    0.09
     composed
    0.09
    double
    0.09
    multiple
    0.09
     двумя
    0.09
     totaling
    0.09
     composto
    0.09
    Multiple
    0.08
     zweimal
    0.08
    Act Density 0.087%

    No Known Activations