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

    Neuronpedia

    INDEX
    Explanations

    completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owards
    -0.07
    (real
    -0.06
    “All
    -0.06
    Church
    -0.06
    ext
    -0.06
     Manual
    -0.06
    .Mutable
    -0.06
     Vector
    -0.06
    Vect
    -0.06
     StringField
    -0.06
    POSITIVE LOGITS
     krb
    0.07
     onStop
    0.07
    -properties
    0.07
     lương
    0.07
    delivery
    0.06
    -header
    0.06
     Julio
    0.06
    rpc
    0.06
    __":↵
    0.06
    ورش
    0.06
    Act Density 0.023%

    No Known Activations