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

    Neuronpedia

    INDEX
    Explanations

    code structures, particularly in programming languages

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

    Code, markup, or foreign language snippets

    np_acts-logits-general · gemini-2.0-flash

    foreign language fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.51
    )‏
    -0.51
     EDS
    -0.50
     Dee
    -0.50
    \}\\
    -0.49
    |}{\
    -0.48
    \
    -0.48
     InputDecoration
    -0.48
     виправивши
    -0.47
    </tr>
    -0.47
    POSITIVE LOGITS
     Bewußt
    0.77
     anún
    0.71
     própri
    0.71
     ainfi
    0.70
     aveug
    0.67
    ſelves
    0.66
     Italij
    0.66
     avoient
    0.66
     valentín
    0.66
     scolaires
    0.66
    Act Density 0.715%

    No Known Activations