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

    Neuronpedia

    INDEX
    Explanations

    special characters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused45>
    0.55
    穴
    0.54
     поха
    0.53
    軐
    0.52
     छेद
    0.52
     kandungan
    0.51
     harvests
    0.51
    arakat
    0.51
     않았
    0.50
    PanelVisual
    0.50
    POSITIVE LOGITS
    l
    0.63
    i
    0.62
    ↵↵
    0.62
    0.59
    </h3>
    0.59
    a
    0.56
    r
    0.51
     England
    0.50
     Key
    0.50
    </h1>
    0.49
    Act Density 0.000%

    No Known Activations