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

    Neuronpedia

    INDEX
    Explanations

    shallow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OutOfBoundsException
    -0.07
     allergies
    -0.06
     peg
    -0.06
    嘉
    -0.06
     oči
    -0.06
    τηγορία
    -0.06
     Catalan
    -0.06
     Cambodia
    -0.06
     extractor
    -0.06
     Share
    -0.06
    POSITIVE LOGITS
     Require
    0.08
    *w
    0.08
     superficial
    0.07
     lac
    0.07
     cru
    0.07
    .fc
    0.06
     Generic
    0.06
     neutrality
    0.06
     sto
    0.06
    vm
    0.06
    Act Density 0.010%

    No Known Activations