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

    Neuronpedia

    INDEX
    Explanations

    shape or form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    huis
    0.44
    <0xBF>
    0.40
    Voor
    0.40
    Highlight
    0.40
     hepatic
    0.39
    ㄕ
    0.38
    εύ
    0.38
    স্ব
    0.38
    Й
    0.38
    Highlights
    0.37
    POSITIVE LOGITS
     Format
    0.40
    imen
    0.38
     कारवाई
    0.38
     Formatting
    0.37
    цени
    0.36
    ਗੇ
    0.36
     advert
    0.36
     nDims
    0.35
    {:
    0.35
    টিআই
    0.35
    Act Density 0.000%

    No Known Activations