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

    Neuronpedia

    INDEX
    Explanations

    word lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     substituents
    0.43
    directed
    0.40
     tér
    0.40
    phosphory
    0.40
    initializer
    0.39
     항목
    0.39
     kur
    0.38
     curbs
    0.38
    stations
    0.37
    pq
    0.37
    POSITIVE LOGITS
    Though
    0.46
    While
    0.45
    യ
    0.44
     दशकों
    0.44
     Religious
    0.43
    宗教
    0.43
     Though
    0.42
    ଥ
    0.41
    Despite
    0.41
    ново
    0.41
    Act Density 0.001%

    No Known Activations