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

    Neuronpedia

    INDEX
    Explanations

    my purpose is to be helpful and harmless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benzer
    0.82
     voyez
    0.77
     parecido
    0.76
     similar
    0.76
     Ditto
    0.76
     مشابه
    0.75
     simili
    0.74
     tweaks
    0.73
     mirip
    0.73
     OTHER
    0.72
    POSITIVE LOGITS
    日益
    1.55
    Nowadays
    1.54
    越来越多的
    1.51
     nowadays
    1.50
     Nowadays
    1.47
     increasingly
    1.44
    越来越
    1.38
     zunehm
    1.35
    越来越多
    1.33
     incessantly
    1.32
    Act Density 0.200%

    No Known Activations