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

    Neuronpedia

    INDEX
    Explanations

    html head and body tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igten
    0.75
     Distress
    0.65
    Fue
    0.65
    小组
    0.65
    ValArr
    0.63
    Span
    0.62
    ilane
    0.62
     குழந்தைகள்
    0.61
    儿
    0.61
    nagyobb
    0.61
    POSITIVE LOGITS
     head
    1.91
    head
    1.75
     Head
    1.67
     HEAD
    1.66
    Head
    1.62
     body
    1.61
    HEAD
    1.51
     header
    1.49
     document
    1.43
     Body
    1.43
    Act Density 0.424%

    No Known Activations