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

    Neuronpedia

    INDEX
    Explanations

    Establishing a theme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.95
     is
    0.58
    to
    0.55
    ॅ
    0.54
     It
    0.52
    <0x0D>
    0.52
     A
    0.52
    ำ
    0.52
    “
    0.51
    ０
    0.51
    POSITIVE LOGITS
    :
    0.73
     σε
    0.65
    ও
    0.64
     في
    0.59
    的名字
    0.58
    ın
    0.53
    も
    0.52
    이란
    0.52
    も含
    0.52
    도
    0.51
    Act Density 0.142%

    No Known Activations