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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     titular
    -0.60
     StringTokenizer
    -0.59
     Efq
    -0.57
     Waray
    -0.57
     مشين
    -0.56
     dinosaurs
    -0.55
     pymongo
    -0.54
    "])
    -0.54
    elfare
    -0.53
     lighter
    -0.53
    POSITIVE LOGITS
    __*/
    0.49
    MergeFrom
    0.47
    PhysRevD
    0.47
    fjspx
    0.46
    MigrationBuilder
    0.46
     looking
    0.45
    FunctionFlags
    0.44
    canestro
    0.44
    IonicModule
    0.44
    IUrlHelper
    0.44
    Act Density 0.001%

    No Known Activations