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

    Neuronpedia

    INDEX
    Explanations

    the word "for," indicating a focus on purpose or function

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

    for the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.70
    ImageContext
    -0.63
     ब्रेकडाउन
    -0.59
     BoxDecoration
    -0.59
    最快更新
    -0.58
     linkovi
    -0.57
     ivelany
    -0.56
     otomatig
    -0.56
    RTLD
    -0.56
    ReusableCell
    -0.54
    POSITIVE LOGITS
     us
    0.43
     allowing
    0.42
    让
    0.38
     prompting
    0.38
    讓
    0.37
     allow
    0.35
     Autorizaciones
    0.34
     stage
    0.34
    Allow
    0.33
     Allow
    0.33
    Act Density 0.162%

    No Known Activations