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

    Neuronpedia

    INDEX
    Explanations

    ideas or observations about your experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ley
    0.57
     theoret
    0.53
     pulsing
    0.49
    ance
    0.48
    น้อย
    0.48
     taxpayers
    0.47
     probationary
    0.46
    йки
    0.46
     retract
    0.45
    plants
    0.45
    POSITIVE LOGITS
    𝘣
    0.48
     Artik
    0.47
     опубликован
    0.47
    慫
    0.46
    Appuntamento
    0.44
     yılları
    0.44
    ここでは
    0.42
     Deps
    0.42
     saham
    0.41
    नात
    0.41
    Act Density 0.004%

    No Known Activations