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

    Neuronpedia

    INDEX
    Explanations

    leave food out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เนื่อง
    0.54
     വിദ
    0.48
     мен
    0.45
     です
    0.44
    ниците
    0.44
    িং
    0.44
     uten
    0.43
     케
    0.43
     말을
    0.43
    нік
    0.43
    POSITIVE LOGITS
     alerts
    0.45
    dumbbell
    0.44
    وأ
    0.43
    Amt
    0.42
    years
    0.41
    decrease
    0.41
    Years
    0.41
    Brooks
    0.40
    seconds
    0.40
     concurs
    0.40
    Act Density 0.000%

    No Known Activations