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

    Neuronpedia

    INDEX
    Explanations

    warnings and error messages related to code execution and data type expectations

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

    technical warnings and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    star
    -0.38
    -0.36
    hand
    -0.36
     fire
    -0.35
    fire
    -0.34
     Pri
    -0.33
     Per
    -0.33
     star
    -0.33
     readily
    -0.32
     go
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.97
    rungsseite
    0.88
     EconPapers
    0.84
    InjectAttribute
    0.73
    tagHelperRunner
    0.71
    uxxxx
    0.71
     intptr
    0.68
    URLException
    0.62
    QMetaType
    0.60
    AndEndTag
    0.57
    Act Density 0.054%
    No Known Activations