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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and definitions in programming code

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

    Code snippets containing type declarations/variables

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.88
     iſt
    -0.79
     Diſ
    -0.75
     purpoſe
    -0.74
    ſelves
    -0.73
     Houſe
    -0.72
     itſelf
    -0.72
     houſe
    -0.70
     unſ
    -0.69
     Conſ
    -0.69
    POSITIVE LOGITS
     s
    0.67
     S
    0.61
     c
    0.57
     v
    0.57
     M
    0.56
    r
    0.55
     C
    0.55
     r
    0.55
     R
    0.52
     Q
    0.51
    Act Density 0.705%

    No Known Activations