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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values and their associated context

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

    start of new lines or answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chham
    -0.58
    rungsseite
    -0.54
    multirow
    -0.53
    endon
    -0.48
    cry
    -0.47
    ziplin
    -0.47
     defy
    -0.47
    utives
    -0.46
    󠁣
    -0.46
    ceder
    -0.46
    POSITIVE LOGITS
     doInBackground
    0.46
     avoient
    0.43
    transQ
    0.42
     snippetHide
    0.38
    ariConfig
    0.38
     vicenda
    0.37
    ChildScrollView
    0.36
    -------
    0.35
     étoient
    0.35
    뀐
    0.34
    Act Density 0.029%

    No Known Activations