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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks within sentences

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

    sentence starts after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.88
     Италијани
    -0.87
     zwiſchen
    -0.83
    IUrlHelper
    -0.82
     indígen
    -0.81
     myſelf
    -0.79
     snippetHide
    -0.77
     estadounid
    -0.77
    <unused8>
    -0.76
     يتيمه
    -0.76
    POSITIVE LOGITS
    
    0.38
    .
    0.38
     also
    0.36
     ,
    0.35
      
    0.33
     has
    0.30
     The
    0.29
     .
    0.29
     and
    0.28
    []
    0.28
    Act Density 0.171%

    No Known Activations