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

    Neuronpedia

    INDEX
    Explanations

    often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рэгістра
    0.51
     простых
    0.50
     აღმასრულებელი
    0.50
    <unused317>
    0.48
    徒
    0.48
    簡単な
    0.47
     परिणामस्वरूप
    0.47
    韮
    0.47
    <unused1778>
    0.47
     ფედერ
    0.47
    POSITIVE LOGITS
    r
    0.63
     ion
    0.48
    i
    0.47
     orientation
    0.46
     gebra
    0.45
     less
    0.44
    a
    0.44
     mast
    0.44
    pub
    0.43
     contains
    0.43
    Act Density 0.006%

    No Known Activations