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

    Neuronpedia

    INDEX
    Explanations

    welcome to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mentioned
    1.11
    similar
    0.94
     mentioned
    0.92
    ilarly
    0.89
    ilst
    0.87
    ierter
    0.83
     آنها
    0.83
     cited
    0.82
     مثلا
    0.82
    erdere
    0.82
    POSITIVE LOGITS
     our
    1.42
    我们的
    1.23
     nosso
    1.16
     oficialmente
    1.16
     officially
    1.15
     paradise
    1.13
     humble
    1.10
     Our
    1.09
     nuestro
    1.08
     nossa
    1.06
    Act Density 0.051%

    No Known Activations