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

    Neuronpedia

    INDEX
    Explanations

    reasons why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guère
    0.67
    ্পর্শ
    0.64
    Depending
    0.63
    avalt
    0.62
     Depending
    0.61
    кість
    0.61
    серед
    0.60
    orent
    0.60
    depending
    0.59
     appartient
    0.59
    POSITIVE LOGITS
     why
    5.57
     reasons
    5.23
    why
    5.16
     Why
    5.09
     reason
    4.98
    Why
    4.90
     Reasons
    4.65
     WHY
    4.60
    WHY
    4.43
    Reasons
    4.42
    Act Density 2.130%

    No Known Activations