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

    Neuronpedia

    INDEX
    Explanations

    run the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Markup
    0.69
    ρκ
    0.64
     ప్రారం
    0.64
     commenc
    0.64
     Execution
    0.63
    Execution
    0.62
     Topical
    0.62
    為主
    0.61
    STATS
    0.61
    ֔
    0.61
    POSITIVE LOGITS
    正确的
    0.84
     distinguir
    0.83
    moral
    0.82
     colesterol
    0.81
     comentario
    0.80
    ူ
    0.80
     venez
    0.80
     correctamente
    0.79
    maximal
    0.78
    请
    0.78
    Act Density 0.011%

    No Known Activations