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

    Neuronpedia

    INDEX
    Explanations

    code related to memory addresses.

    oai_token-act-pair · gemini-2.0-flash

    say "p" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.60
    ↵
    -0.55
    </strong>
    -0.55
    <unused63>
    -0.54
    <unused61>
    -0.52
    V
    -0.52
    <eos>
    -0.50
    1
    -0.49
    T
    -0.49
    <strong>
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    1.20
     BoxFit
    1.09
    DockStyle
    1.08
     مشين
    1.05
     المعيارى
    1.04
    styleType
    1.02
    extAlignment
    1.01
    IntoConstraints
    0.98
     surla
    0.96
     esternos
    0.95
    Act Density 4.716%

    No Known Activations