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

    Neuronpedia

    INDEX
    Explanations

    achieve progressive realization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WillAppear
    0.43
     catching
    0.40
     echoing
    0.38
    lineTo
    0.38
    প্তর
    0.38
     Israël
    0.38
    helf
    0.35
    дяки
    0.35
    ifié
    0.35
    捙
    0.35
    POSITIVE LOGITS
     sabem
    0.40
     Dix
    0.38
    NPC
    0.38
     Informed
    0.38
    桨
    0.37
    прави
    0.36
    ਊ
    0.36
     ю
    0.36
    overflow
    0.35
     secession
    0.35
    Act Density 0.003%

    No Known Activations