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

    Neuronpedia

    INDEX
    Explanations

    Okay, here are a few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     let
    0.60
     letting
    0.60
     इत
    0.58
    etu
    0.55
     –
    0.55
     aspirations
    0.55
    ewise
    0.55
    etable
    0.54
    तमंद
    0.54
     pitch
    0.54
    POSITIVE LOGITS
     Here
    0.94
     here
    0.92
     aqui
    0.88
     aquí
    0.82
    Here
    0.81
     Güzel
    0.81
    !।
    0.81
    دیا
    0.80
     HERE
    0.79
    ！
    0.78
    Act Density 0.122%

    No Known Activations