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

    Neuronpedia

    INDEX
    Explanations

    comments and documentation in the code

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

    Code comments and notes

    np_acts-logits-general · gemini-2.0-flash

    notes and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.63
     thereafter
    -0.49
    ViewInit
    -0.49
     whereof
    -0.48
     AssemblyCulture
    -0.48
     mxArray
    -0.47
    ItemLayout
    -0.46
     opri
    -0.44
     accordingly
    -0.44
     thereupon
    -0.44
    POSITIVE LOGITS
     Note
    0.78
     NOTE
    0.77
     FIXME
    0.73
     note
    0.73
     We
    0.72
    kijken
    0.68
     Shouldn
    0.67
    NOTE
    0.66
     If
    0.66
    Надо
    0.65
    Act Density 0.146%

    No Known Activations