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

    Neuronpedia

    INDEX
    Explanations

    href

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Свят
    -0.07
    VIEW
    -0.06
     пр
    -0.06
    actions
    -0.06
    коз
    -0.06
     clause
    -0.06
    ันด
    -0.06
    具
    -0.06
    言って
    -0.06
     UPS
    -0.06
    POSITIVE LOGITS
     Leslie
    0.07
     dostal
    0.07
    ows
    0.06
    Power
    0.06
     decorations
    0.06
     llama
    0.06
    mime
    0.06
    ivan
    0.06
    declar
    0.06
     isol
    0.06
    Act Density 0.016%

    No Known Activations