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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity or persistence despite challenges

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

    still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.59
    市镇
    -0.58
    PreferredItem
    -0.54
    findpost
    -0.52
    fromnode
    -0.52
    balleur
    -0.50
     BrowserModule
    -0.50
    PMailer
    -0.49
    postmedia
    -0.48
    ViewImports
    -0.47
    POSITIVE LOGITS
    eth
    0.45
    fortawesome
    0.43
    all
    0.42
    ins
    0.42
     urmă
    0.42
    A
    0.42
    a
    0.41
    y
    0.40
    un
    0.40
    w
    0.40
    Act Density 0.016%

    No Known Activations