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

    Neuronpedia

    INDEX
    Explanations

    instances of language indicating citation, attribution, or references

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

    legal and technical notations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '],
    -0.60
    '},
    -0.59
     "",
    -0.56
     "")
    -0.55
    ']}
    -0.54
    '),
    -0.54
    '}>
    -0.52
     ""),
    -0.51
    '}),
    -0.51
    ’，
    -0.51
    POSITIVE LOGITS
     AssemblyCulture
    0.75
    PerformLayout
    0.73
    endphp
    0.71
     CreateTagHelper
    0.70
    twimg
    0.67
     שוליים
    0.67
     متعلقه
    0.66
    __(/*!
    0.65
    ंदीखरीदारी
    0.65
    exels
    0.64
    Act Density 0.171%

    No Known Activations