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

    Neuronpedia

    INDEX
    Explanations

    problems and help with tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sự
    0.84
     amelyet
    0.82
    melidir
    0.81
     rendelkez
    0.80
     intervento
    0.79
     rencana
    0.77
     posee
    0.76
    具有
    0.76
     posiada
    0.76
    gaben
    0.75
    POSITIVE LOGITS
     designing
    2.85
     trying
    2.84
     doing
    2.75
     selecting
    2.72
     installing
    2.70
     navigating
    2.66
     collecting
    2.66
     researching
    2.65
     distributing
    2.65
     analyzing
    2.63
    Act Density 0.352%

    No Known Activations