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

    Neuronpedia

    INDEX
    Explanations

    access or check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :)
    0.79
    <h1>
    0.72
     맛있
    0.71
    瞑
    0.68
    ことができます
    0.67
    <h3>
    0.66
     Tento
    0.66
     Raut
    0.66
     Telescope
    0.65
     বাঁধবেন
    0.65
    POSITIVE LOGITS
    Access
    0.86
    নীতিক
    0.80
     pathological
    0.78
    filesystem
    0.78
     controversial
    0.76
     humeral
    0.74
    iciais
    0.74
     unilaterally
    0.74
    Check
    0.73
     hypogly
    0.73
    Act Density 0.000%

    No Known Activations