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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    merksam
    0.40
     Accom
    0.39
     While
    0.38
    URNING
    0.38
    фика
    0.37
    甚至
    0.37
     cultivating
    0.37
    ੰਜ
    0.37
    िग
    0.36
    ime
    0.36
    POSITIVE LOGITS
    ܣ
    0.52
    symmetric
    0.50
     ഉയ
    0.46
    ли
    0.43
     नॉ
    0.43
     붙
    0.43
     ጉ
    0.42
     ভ্রমণের
    0.42
     მშ
    0.42
     노래
    0.42
    Act Density 0.000%

    No Known Activations