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

    Neuronpedia

    INDEX
    Explanations

    examples like e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    commerce
    0.84
    Commerce
    0.81
    uring
    0.77
     commerce
    0.77
    ologii
    0.76
    ocracy
    0.71
     marché
    0.71
     Commerce
    0.71
    ulent
    0.70
     riddled
    0.69
    POSITIVE LOGITS
    g
    0.96
     g
    0.70
    下标
    0.64
     гар
    0.64
    /:
    0.63
    ג
    0.62
     궁
    0.61
     gate
    0.59
     இறு
    0.58
     hal
    0.58
    Act Density 0.016%

    No Known Activations