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

    Neuronpedia

    INDEX
    Explanations

    affirmations or confirmations of correctness and legality

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

    affirmation and well-being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qvarna
    -0.54
    FromNib
    -0.52
     пузы
    -0.51
    Билгалдахарш
    -0.50
    uyasha
    -0.49
    glPushMatrix
    -0.49
     informée
    -0.48
     CONSUMER
    -0.47
     estekak
    -0.47
    ragamo
    -0.47
    POSITIVE LOGITS
     Alright
    1.65
    Alright
    1.61
     alright
    1.58
    alright
    1.48
     okay
    0.70
     OKAY
    0.65
     Okay
    0.59
    okay
    0.57
    Okay
    0.55
     OK
    0.55
    Act Density 0.003%

    No Known Activations