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

    Neuronpedia

    INDEX
    Explanations

    instances of inquiries or concerns raised in a context

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

    Followed by "any"

    np_acts-logits-general · gemini-2.0-flash

    any issues or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fometimes
    -0.65
     bazen
    -0.59
    Климат
    -0.54
    seamnă
    -0.54
     whereof
    -0.51
    kadang
    -0.50
     sometimes
    -0.49
     mêmes
    -0.49
    sometimes
    -0.48
     often
    -0.48
    POSITIVE LOGITS
     whatsoever
    0.89
     apapun
    0.69
    SizeF
    0.66
     Any
    0.65
     any
    0.65
     فريبيس
    0.64
    AnchorStyles
    0.63
    FailureListener
    0.62
    openzeppelin
    0.62
    RTCF
    0.61
    Act Density 0.251%

    No Known Activations