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

    Neuronpedia

    INDEX
    Explanations

    offering or inquiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dual
    0.48
     wins
    0.47
    amanya
    0.46
     high
    0.46
     nicht
    0.46
     jarang
    0.46
     venenatis
    0.45
    }$&$
    0.45
    回事
    0.45
     ওরফে
    0.44
    POSITIVE LOGITS
    Please
    1.09
     Please
    1.08
    Hopefully
    1.07
    Here
    1.01
    Would
    0.99
     Hopefully
    0.93
     PLEASE
    0.92
    PLEASE
    0.90
     Here
    0.90
     Would
    0.90
    Act Density 2.833%

    No Known Activations