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

    Neuronpedia

    INDEX
    Explanations

    formatted code segments or comments

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

    math delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comp
    -0.46
     Hark
    -0.45
    単
    -0.45
     ind
    -0.41
     operating
    -0.40
     Rü
    -0.39
     ре
    -0.39
     McCl
    -0.39
     mag
    -0.39
     operational
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    0.80
    IndentedString
    0.63
    GEBURTSDATUM
    0.60
     tartalomajánló
    0.58
     autorytatywna
    0.57
     wireType
    0.56
    səhifə
    0.54
     ivelany
    0.53
     OMITBAD
    0.53
     ddelwed
    0.52
    Act Density 0.000%

    No Known Activations