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

    Neuronpedia

    INDEX
    Explanations

    rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crud
    -0.07
    323
    -0.06
    .setEditable
    -0.06
    (getClass
    -0.06
    Fonts
    -0.06
     COLORS
    -0.06
    친
    -0.06
     colors
    -0.06
     destroy
    -0.06
    cu
    -0.06
    POSITIVE LOGITS
     Surg
    0.06
    อากาศ
    0.06
    Liverpool
    0.06
    htags
    0.06
     dicts
    0.06
    ?"↵↵↵↵
    0.06
    enne
    0.06
    ESTAMP
    0.06
     bod
    0.06
    ropoda
    0.06
    Act Density 0.355%

    No Known Activations