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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    動物
    0.55
    cidos
    0.50
    Deploy
    0.50
     {}
    0.50
     ぐらい
    0.49
    畳
    0.49
     deployed
    0.48
     डांस
    0.48
    席
    0.48
     deployments
    0.47
    POSITIVE LOGITS
     Rhodesia
    0.64
     Zhuang
    0.62
     Allende
    0.62
     Schwarzenegger
    0.62
     provenance
    0.60
     patina
    0.59
     Padilla
    0.57
     flaw
    0.56
     encontraron
    0.56
     wartime
    0.56
    Act Density 0.000%

    No Known Activations