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

    Neuronpedia

    INDEX
    Explanations

    own understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fertile
    -0.11
     pr
    -0.10
     gag
    -0.10
     hors
    -0.10
    annes
    -0.09
     Bent
    -0.09
     McCoy
    -0.09
     births
    -0.09
    æĸĩ
    -0.09
     ot
    -0.09
    POSITIVE LOGITS
    unsch
    0.10
    _Pin
    0.09
     shoot
    0.09
    _PUSHDATA
    0.09
    ilig
    0.09
    Clipboard
    0.09
    ,:,
    0.09
    datagrid
    0.09
    çł
    0.09
    CONDITION
    0.09
    Act Density 0.013%

    No Known Activations