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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX commands and math symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.91
     indígen
    -0.82
    rrggbb
    -0.80
     iſt
    -0.79
     Meksiku
    -0.76
     témoig
    -0.71
     queſta
    -0.69
    AndroidJUnit
    -0.69
    afficheront
    -0.68
    تقاوى
    -0.68
    POSITIVE LOGITS
     \
    0.85
    \
    0.78
     $\
    0.60
    ]\
    0.57
    :\
    0.55
    |\
    0.53
    $\
    0.53
    {\
    0.52
    (/\
    0.52
    }\
    0.51
    Act Density 0.035%

    No Known Activations