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

    Neuronpedia

    INDEX
    Explanations

    code constructs and elements related to API service handling and data structure management

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

    Code, logs, or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '],
    -0.69
    ++
    -0.64
    ++)
    -0.62
    »),
    -0.60
    '),
    -0.60
    '))
    -0.59
    '])
    -0.58
    "):
    -0.58
    ?>">
    -0.57
    ],\
    -0.57
    POSITIVE LOGITS
     Cæsar
    0.81
     Shakspeare
    0.80
    _
    0.76
     Anſ
    0.70
     Diſ
    0.68
    Such
    0.67
     Heav
    0.66
     Esau
    0.66
    R
    0.64
     Shaksp
    0.64
    Act Density 1.367%

    No Known Activations