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

    Neuronpedia

    INDEX
    Explanations

    directions, cases, and endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    0.86
    ד
    0.85
    ס
    0.71
    ت
    0.70
    تون
    0.68
    тона
    0.66
    dengan
    0.66
    درا
    0.65
    きた
    0.64
    такт
    0.64
    POSITIVE LOGITS
    vis
    0.64
    𝘽
    0.64
    ide
    0.63
    zing
    0.61
    㶲
    0.59
     poté
    0.58
    剂
    0.58
    ified
    0.57
    ）,
    0.57
    нг
    0.56
    Act Density 0.004%

    No Known Activations