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

    Neuronpedia

    INDEX
    Explanations

    allergies and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    minimum
    0.48
     minimum
    0.45
    Minimum
    0.42
    calculate
    0.42
     Minimum
    0.41
    mensaje
    0.39
     incomes
    0.39
    tree
    0.39
    opening
    0.39
    itmen
    0.38
    POSITIVE LOGITS
    Cab
    0.43
     antérieur
    0.41
    潮
    0.41
    暠
    0.40
     Cab
    0.40
     '../../../
    0.39
    Pumpkin
    0.38
     каби
    0.38
    PLAIN
    0.38
     ยาก
    0.38
    Act Density 0.000%

    No Known Activations