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

    Neuronpedia

    INDEX
    Explanations

    statements that emphasize noteworthy observations and conclusions

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

    pointing out a fact followed by "that"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.39
     testGet
    -0.36
     насељу
    -0.36
     Efq
    -0.36
    Pyx
    -0.36
     ſte
    -0.36
    MockBean
    -0.35
    ":[{
    -0.35
     sane
    -0.35
    Népesség
    -0.34
    POSITIVE LOGITS
    httphttps
    0.63
    sidemargin
    0.54
    AndEndTag
    0.52
    MessageOf
    0.50
    rungsseite
    0.49
     INTERESAR
    0.48
    atschappij
    0.46
    AddTagHelper
    0.45
    aarrggbb
    0.45
    \{\\
    0.44
    Act Density 0.161%

    No Known Activations