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

    Neuronpedia

    INDEX
    Explanations

    allow many users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     breathable
    0.56
     cosplay
    0.50
     breathing
    0.49
     invigorating
    0.49
     leucine
    0.49
     marinated
    0.48
     ruined
    0.47
    aphthalene
    0.46
    ྱ
    0.46
     phosphate
    0.45
    POSITIVE LOGITS
     Shaped
    0.54
    ق
    0.50
     Execute
    0.49
     Technical
    0.49
    是一
    0.48
     Schedules
    0.48
    أ
    0.48
    ى
    0.48
     Networks
    0.47
    ések
    0.47
    Act Density 0.000%

    No Known Activations