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

    Neuronpedia

    INDEX
    Explanations

    lines that import packages in Java

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    findpost
    -0.70
     initComponents
    -0.54
     contributions
    -0.50
     AssemblyCompany
    -0.48
    rufe
    -0.47
    postsleuth
    -0.47
    styleable
    -0.46
    MarshalTo
    -0.45
     taxes
    -0.45
    Tarifs
    -0.42
    POSITIVE LOGITS
     Reviewed
    0.63
    Datuak
    0.58
     Walkover
    0.56
    onatos
    0.54
    conduct
    0.54
    KURZBESCHREIBUNG
    0.53
     récompenses
    0.53
    AnchorTagHelper
    0.53
     Zier
    0.52
     Breakers
    0.51
    Act Density 0.402%

    No Known Activations