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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒐪
    0.70
    /−
    0.56
     Magento
    0.55
     Kursk
    0.55
     ServiceNow
    0.54
     SharePoint
    0.54
    )–
    0.54
     antitrust
    0.53
     situación
    0.53
     ✅
    0.53
    POSITIVE LOGITS
    %\
    1.73
     \
    1.47
     %\
    1.45
    \
    1.41
    %
    1.41
     %
    1.38
    {\
    1.19
    %%\
    1.05
     \%\
    1.05
    %%%%%%%%%%%%%%%%
    1.03
    Act Density 0.015%

    No Known Activations