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

    Neuronpedia

    INDEX
    Explanations

    Third unheard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     аккумулятор
    0.45
    #'
    0.42
     поддержка
    0.42
    ã
    0.41
     सप्टेंबर
    0.41
     Maryland
    0.41
     Atlético
    0.41
    +'
    0.41
     académ
    0.40
    county
    0.40
    POSITIVE LOGITS
    溶解
    0.45
     Rahul
    0.44
     Mahesh
    0.44
     disagreement
    0.44
     Imran
    0.42
     divergences
    0.41
     sker
    0.41
    en
    0.41
     unjustified
    0.41
    েলে
    0.40
    Act Density 0.002%

    No Known Activations