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

    Neuronpedia

    INDEX
    Explanations

    resource gathering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cem
    0.42
    Conte
    0.40
    ાઈ
    0.39
    Thomas
    0.38
     contigo
    0.38
     ge
    0.37
     shouldn
    0.37
    fre
    0.36
    ጻ
    0.36
     ounces
    0.36
    POSITIVE LOGITS
    ˣ
    0.40
     很
    0.40
     карта
    0.39
    MDEwOlJlcG
    0.38
     банков
    0.38
    جاتا
    0.38
     valueForKey
    0.38
     карты
    0.38
    扳
    0.38
     Duck
    0.38
    Act Density 0.000%

    No Known Activations