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

    Neuronpedia

    INDEX
    Explanations

    seeing and finding out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Examine
    0.79
     analys
    0.71
     살펴
    0.69
     формат
    0.66
     Defines
    0.66
     анали
    0.66
    acije
    0.65
     Changel
    0.65
     ozn
    0.64
    ஶ
    0.64
    POSITIVE LOGITS
    ING
    0.71
    <0x9D>
    0.63
    0.63
    <0xA5>
    0.60
    <0xA1>
    0.59
    いき
    0.58
    <0xB1>
    0.57
    <0xB4>
    0.56
    <0x98>
    0.56
    <0x83>
    0.55
    Act Density 0.117%

    No Known Activations