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

    Neuronpedia

    INDEX
    Explanations

    computer files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enrich
    -0.06
    	Vec
    -0.06
    addElement
    -0.06
    incinnati
    -0.06
    mux
    -0.06
    mos
    -0.06
     adversary
    -0.06
    .dt
    -0.06
     عرضه
    -0.06
     AIS
    -0.06
    POSITIVE LOGITS
     freel
    0.06
    Very
    0.06
     би
    0.06
     Orchard
    0.06
     largely
    0.06
    い
    0.06
    than
    0.06
     geometric
    0.06
    .sulake
    0.06
     cripp
    0.06
    Act Density 0.065%

    No Known Activations