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

    Neuronpedia

    INDEX
    Explanations

    non-standard quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Handicap
    -0.09
     helpless
    -0.08
     Thom
    -0.08
     ventes
    -0.08
    ğiz
    -0.08
     álbum
    -0.08
    ainte
    -0.08
    Henry
    -0.08
     altru
    -0.08
     jointly
    -0.08
    POSITIVE LOGITS
     escaped
    0.09
    escaped
    0.09
    ergenic
    0.08
     reopened
    0.08
     reopening
    0.08
     knitting
    0.08
     الكيمي
    0.08
     encl
    0.08
    ijih
    0.08
    打不开
    0.08
    Act Density 0.005%

    No Known Activations