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

    Neuronpedia

    INDEX
    Explanations

    viewing items or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    は
    0.88
    ید
    0.88
    는
    0.78
    ב
    0.77
    çı
    0.74
    টি
    0.73
    ități
    0.72
    표
    0.71
    ۔
    0.70
    บริการ
    0.70
    POSITIVE LOGITS
    er
    0.55
     leuke
    0.55
     reduc
    0.54
    ش
    0.53
     Crucible
    0.52
    age
    0.52
     Superhero
    0.51
    aste
    0.51
    rians
    0.50
    ;?>
    0.50
    Act Density 0.006%

    No Known Activations