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

    Neuronpedia

    INDEX
    Explanations

    context of this sentence/phrase/message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generated
    0.69
     justifies
    0.67
    Causes
    0.66
     substantiate
    0.65
     simplifies
    0.65
    ிக
    0.65
    혁
    0.65
     justify
    0.64
     얻
    0.63
     المقدم
    0.62
    POSITIVE LOGITS
     requirement
    0.91
     decisione
    0.85
     announcement
    0.84
     grabación
    0.84
    bedarf
    0.82
    wunsch
    0.82
    requirement
    0.82
     sighting
    0.81
    awareness
    0.80
     желание
    0.79
    Act Density 0.076%

    No Known Activations