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

    Neuronpedia

    INDEX
    Explanations

    specific names and proper nouns

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

    ending in "tt", "ss", "ARR", "Azz"

    np_acts-logits-general · gemini-2.0-flash

    Azz, ARR, Ott, mann

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    -0.71
    actionBar
    -0.57
    位
    -0.56
    ❷
    -0.56
    рои
    -0.55
    望
    -0.55
     Bourgoin
    -0.55
    도
    -0.54
    érieurs
    -0.54
    en
    -0.54
    POSITIVE LOGITS
     Coss
    0.91
     Azz
    0.91
    CrossRef
    0.90
    Yess
    0.86
     Utt
    0.85
     OSS
    0.84
    edd
    0.84
    MethodManager
    0.82
    Ayy
    0.82
     Genn
    0.80
    Act Density 0.749%

    No Known Activations