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

    Neuronpedia

    INDEX
    Explanations

    URLs and domain names, specifically those related to social media and organization links

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

    URLs with domain paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.68
     <<<<<<<<<<<<<<
    -0.57
     ddelweddau
    -0.52
     faſt
    -0.51
    erintah
    -0.49
    GTCX
    -0.48
    SourceChecksum
    -0.47
    ervlak
    -0.46
    ſelf
    -0.46
     abſ
    -0.45
    POSITIVE LOGITS
    /@
    0.50
    USERNAME
    0.45
    {@
    0.43
     (@
    0.41
     @
    0.41
     username
    0.41
    username
    0.41
    BeginContext
    0.40
    @
    0.39
    =@
    0.39
    Act Density 0.005%

    No Known Activations