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

    Neuronpedia

    INDEX
    Explanations

    included

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pl
    -0.07
    ifers
    -0.06
     cloning
    -0.06
     Mormon
    -0.06
     mad
    -0.06
    Caption
    -0.06
     Lite
    -0.06
    leads
    -0.06
     CSC
    -0.06
     Jeh
    -0.06
    POSITIVE LOGITS
    .forEach
    0.07
    ้าส
    0.07
     αδ
    0.07
    imers
    0.07
     ilk
    0.07
    ωση
    0.06
    jes
    0.06
     oauth
    0.06
    (sql
    0.06
     ()->
    0.06
    Act Density 0.030%

    No Known Activations