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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or prompts

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

    The code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.61
     AssemblyTitle
    -0.59
    PMailer
    -0.58
    ReusableCell
    -0.57
     Efq
    -0.54
     zwiſchen
    -0.54
    endphp
    -0.54
     indígen
    -0.53
    <pad>
    -0.52
     Geſch
    -0.52
    POSITIVE LOGITS
    assertNotNull
    0.34
     "
    0.33
    !!!
    0.30
     pic
    0.29
    clu
    0.29
     fast
    0.29
    BufferException
    0.29
     similaire
    0.28
    participants
    0.28
     peny
    0.28
    Act Density 0.724%

    No Known Activations