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

    Neuronpedia

    INDEX
    Explanations

    key comparisons between similar platforms and their features

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

    punctuation and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Garrison
    -0.54
    ContentAsync
    -0.52
    ilien
    -0.47
    __':
    -0.47
    amentlich
    -0.46
    WireFormatLite
    -0.46
    __":
    -0.46
    ftagPool
    -0.46
    urlopen
    -0.46
    ੝
    -0.46
    POSITIVE LOGITS
    ſelf
    0.43
    MessageOf
    0.40
     ugyan
    0.37
     فريبيس
    0.35
     BrowserModule
    0.35
     varandra
    0.35
    ſelves
    0.35
    同样的
    0.33
    eseorang
    0.32
    utuhkan
    0.32
    Act Density 0.165%

    No Known Activations