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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.60
     PublicKey
    -0.57
     Mandy
    -0.56
    localctx
    -0.55
     IDENTITY
    -0.55
     middle
    -0.54
     Ammon
    -0.54
     Mildred
    -0.53
    تفصیلات
    -0.53
    migrationBuilder
    -0.52
    POSITIVE LOGITS
    aves
    0.65
    evos
    0.57
    awaiter
    0.53
    ThroughAttribute
    0.52
    AVES
    0.50
    XmlAccessorType
    0.50
    EDEFAULT
    0.46
    resave
    0.46
     easel
    0.46
    ave
    0.46
    Act Density 0.013%

    No Known Activations