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

    Neuronpedia

    INDEX
    Explanations

    words related to proposing ideas, opinions, or providing judgement

    oai_token-act-pair · gemini-2.0-flash

    suggest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timur
    -0.51
    vény
    -0.49
    XG
    -0.48
    jeuner
    -0.47
     useRef
    -0.46
     repro
    -0.44
    هاد
    -0.43
    laken
    -0.43
     chives
    -0.43
     rå
    -0.42
    POSITIVE LOGITS
     تضيفلها
    1.05
     مشين
    0.91
    новништво
    0.79
    viewDidLoad
    0.73
    TintMode
    0.71
    ="@+
    0.68
    complexContent
    0.66
    DeleteBehavior
    0.65
    RegistryLite
    0.65
    ReusableCell
    0.65
    Act Density 7.089%

    No Known Activations