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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    󠁢
    -0.92
    Personensuche
    -0.88
    TagMode
    -0.80
    -0.79
    migrationBuilder
    -0.76
    ConstraintMaker
    -0.73
    msgTypes
    -0.72
    ⓧ
    -0.71
    AddTagHelper
    -0.70
    хьтан
    -0.69
    POSITIVE LOGITS
     familles
    0.51
     industriale
    0.42
    お待ちしております
    0.42
     family
    0.40
     families
    0.38
     Clusters
    0.38
     marriage
    0.37
     verheiratet
    0.37
    ToArray
    0.36
    的是
    0.35
    Act Density 0.000%

    No Known Activations