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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.82
     '\\;'
    -0.75
    <bos>
    -0.73
    bootstrapcdn
    -0.73
    AddTagHelper
    -0.68
     mergeFrom
    -0.68
     nonatomic
    -0.61
    SerializedName
    -0.59
    FormTagHelper
    -0.59
     EconPapers
    -0.59
    POSITIVE LOGITS
     inquis
    0.48
     certiorari
    0.42
     melatonin
    0.42
     Inventories
    0.42
     Mache
    0.42
     Conscience
    0.42
     censi
    0.41
    hiba
    0.41
     imparti
    0.41
    ɟ
    0.40
    Act Density 0.049%

    No Known Activations