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

    Neuronpedia

    INDEX
    Explanations

    react use hooks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xAC>
    0.63
    м
    0.60
    г
    0.60
    ل
    0.60
    to
    0.59
    ا
    0.59
    س
    0.58
    о
    0.57
    ম
    0.57
    de
    0.55
    POSITIVE LOGITS
    岔
    0.52
     控制
    0.51
    িয়ের
    0.51
    ぎ
    0.50
    ñón
    0.49
    φος
    0.49
    <unused1905>
    0.49
    養
    0.49
    䙷
    0.49
     กับ
    0.48
    Act Density 0.001%

    No Known Activations