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

    Neuronpedia

    INDEX
    Explanations

    Origin, primary sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reproducción
    0.52
    вод
    0.52
    orben
    0.51
    áculo
    0.50
     inici
    0.50
     gera
    0.49
    asah
    0.49
     rueda
    0.48
     território
    0.47
    okban
    0.47
    POSITIVE LOGITS
    Mrs
    0.47
     WhatsApp
    0.44
     drone
    0.44
     blockchain
    0.44
    年の
    0.44
     بولی
    0.41
    ש
    0.41
    la
    0.40
     sparsity
    0.40
     Millennials
    0.39
    Act Density 0.003%

    No Known Activations