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

    Neuronpedia

    INDEX
    Explanations

    phrases related to account management or verification processes

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

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    Russian verbs and English substrings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.09
     houſe
    -1.03
     purpoſe
    -0.97
     Majefty
    -0.94
     ſche
    -0.93
    存于互联网档案馆
    -0.91
     ſever
    -0.89
     beſt
    -0.87
     themſelves
    -0.85
     ſta
    -0.85
    POSITIVE LOGITS
     את
    0.71
     свою
    0.54
    amerikanische
    0.51
    сь
    0.50
    рию
    0.49
     einen
    0.49
     «
    0.49
     entire
    0.49
     vast
    0.48
     erforder
    0.48
    Act Density 0.013%

    No Known Activations