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

    Neuronpedia

    INDEX
    Explanations

    technical details related to software development and version control

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

    Hexadecimal characters

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings like git hashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -1.28
     itſelf
    -1.20
     myſelf
    -1.19
    ſelves
    -1.15
     themſelves
    -1.13
     Monfieur
    -1.12
     houſe
    -1.12
     iſt
    -1.09
     Efq
    -1.08
     pleaſure
    -1.07
    POSITIVE LOGITS
     c
    0.84
     d
    0.81
    c
    0.80
    ca
    0.77
    f
    0.76
     b
    0.75
     f
    0.74
    e
    0.73
    b
    0.73
     e
    0.71
    Act Density 1.108%

    No Known Activations