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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the selection and identification of correct items or actions

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

    Followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    solve math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgSender
    -0.71
    ETHING
    -0.60
    angliski
    -0.57
     henvisninger
    -0.56
    phazard
    -0.55
    [@"
    -0.54
    imanapun
    -0.53
     overnight
    -0.52
    umbersome
    -0.51
    brunn
    -0.51
    POSITIVE LOGITS
     صوتيه
    0.74
    Rhestr
    0.59
     تضيفلها
    0.57
    Filmografie
    0.54
    andidate
    0.51
    Tembelea
    0.51
    __":
    0.50
     سكانية
    0.49
    ///</
    0.49
    AddTagHelper
    0.48
    Act Density 0.503%

    No Known Activations