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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.40
     مہارت
    0.39
    و
    0.38
    বার্গ
    0.37
    وم
    0.36
    鋆
    0.36
    bikes
    0.35
    en
    0.35
    "،
    0.35
    ور
    0.34
    POSITIVE LOGITS
    <0x89>
    0.57
    PreferredItem
    0.45
    <0xBE>
    0.42
     multiSelectList
    0.42
    <0x84>
    0.41
     finalText
    0.41
     namik
    0.41
     예를
    0.41
    <0x8E>
    0.41
     confronts
    0.41
    Act Density 0.001%

    No Known Activations