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

    Neuronpedia

    INDEX
    Explanations

    links and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tell
    0.82
     telling
    0.73
     detachment
    0.73
     ions
    0.71
     cell
    0.69
     patch
    0.69
     patches
    0.68
     cells
    0.67
    ères
    0.67
     niet
    0.66
    POSITIVE LOGITS
     받을
    0.79
    <unused24>
    0.76
    pèce
    0.70
    кати
    0.68
     itth
    0.68
    ColorLegend
    0.67
     TInner
    0.66
    লিখ
    0.66
    <unused2>
    0.66
    𝘱
    0.66
    Act Density 0.013%

    No Known Activations