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

    Neuronpedia

    INDEX
    Explanations

    authors of academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Denovo
    0.35
     फुलकारी
    0.34
    蠣
    0.32
    PlatformToolset
    0.31
    ➰
    0.30
     antennis
    0.30
    PERATURE
    0.30
    Watercolor
    0.29
     Cytol
    0.29
     ALPINE
    0.29
    POSITIVE LOGITS
     K
    0.46
     van
    0.46
     Kumar
    0.46
     David
    0.46
     Michael
    0.46
     Martin
    0.45
     Peter
    0.44
     John
    0.44
     Richard
    0.44
     Gupta
    0.44
    Act Density 0.012%

    No Known Activations